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

    Neuronpedia

    INDEX
    Explanations

    references to issues or challenges

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

    problem and problem solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цездатний
    -0.56
    ../../../
    -0.53
    などに
    -0.53
    OGND
    -0.52
    curacies
    -0.52
    ților
    -0.51
    ふと
    -0.49
    estries
    -0.48
     heerlijk
    -0.48
    ricanes
    -0.48
    POSITIVE LOGITS
     problem
    1.95
    problem
    1.84
    Problem
    1.81
     Problem
    1.73
     PROBLEM
    1.59
    PROBLEM
    1.48
     probleem
    1.27
     problème
    1.23
     problema
    1.14
    Problema
    1.02
    Act Density 0.015%

    No Known Activations