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

    Neuronpedia

    INDEX
    Explanations

    .gnu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cfg
    -0.08
    _checkpoint
    -0.08
     what
    -0.07
    Transform
    -0.07
     figures
    -0.07
    Crow
    -0.07
    ジャン
    -0.07
     Crow
    -0.07
    Queue
    -0.06
    Meteor
    -0.06
    POSITIVE LOGITS
    隔音
    0.08
    	dfs
    0.07
     MSNBC
    0.07
    adients
    0.07
    pane
    0.07
    吁
    0.06
    _similarity
    0.06
    ':↵↵
    0.06
    otonin
    0.06
     öğretmen
    0.06
    Act Density 0.001%

    No Known Activations