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

    Neuronpedia

    INDEX
    Explanations

    thinking step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Propagation
    0.40
    And
    0.39
    Atlant
    0.37
    Abstract
    0.37
    Twenty
    0.37
    وق
    0.35
    No
    0.35
    Thirty
    0.34
    Song
    0.34
    abstract
    0.34
    POSITIVE LOGITS
     EP
    0.53
     Problem
    0.51
     PROBLEM
    0.49
     PB
    0.46
     PS
    0.43
     Assume
    0.43
     PF
    0.42
     समस्या
    0.41
     Bring
    0.41
     Listing
    0.40
    Act Density 0.000%

    No Known Activations