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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eq
    -0.08
    扛
    -0.07
     "#{
    -0.07
     Recogn
    -0.07
    ,time
    -0.07
     Cannot
    -0.07
    Factors
    -0.07
    —and
    -0.07
     Loc
    -0.06
    ()==
    -0.06
    POSITIVE LOGITS
    前述
    0.07
    RefPtr
    0.07
    הפ
    0.07
     Provided
    0.07
    .MessageBox
    0.07
     준
    0.07
     Cobra
    0.06
    岈
    0.06
    /S
    0.06
    ara
    0.06
    Act Density 0.057%

    No Known Activations