Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to identifying or discussing problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "problem" or "problems"

    np_acts-logits-general · gemini-2.0-flash

    describing a problem or its fix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.60
    MLLoader
    -0.58
    Clips
    -0.58
    sements
    -0.52
    AnchorStyles
    -0.52
     насеље
    -0.51
    eleste
    -0.50
     recevez
    -0.50
    abaret
    -0.48
     culturali
    -0.48
    POSITIVE LOGITS
     problems
    1.31
     Problems
    1.27
    Problems
    1.20
     Problem
    1.20
    PROBLEM
    1.20
     PROBLEM
    1.15
     PROBLEMS
    1.10
    Problem
    1.10
     problem
    1.10
    problems
    1.10
    Act Density 0.134%

    No Known Activations