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

    Neuronpedia

    INDEX
    Explanations

    ybrid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .factor
    -0.08
    æ
    -0.08
    \Admin
    -0.08
    .paused
    -0.07
    IU
    -0.07
     balk
    -0.07
    <table
    -0.07
    .notify
    -0.07
    <N
    -0.07
    CallCheck
    -0.07
    POSITIVE LOGITS
    .workflow
    0.07
    쎅
    0.07
    Arizona
    0.07
    .wav
    0.06
     reversed
    0.06
    Removing
    0.06
    ImageRelation
    0.06
     가운
    0.06
     העבוד
    0.06
    퍅
    0.06
    Act Density 0.016%

    No Known Activations