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

    Neuronpedia

    INDEX
    Explanations

    appeal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .should
    -0.08
    里的
    -0.07
    _column
    -0.07
    .child
    -0.07
     встреча
    -0.07
    明朗
    -0.07
    (localStorage
    -0.07
     indx
    -0.07
     rebounds
    -0.07
    .Parcel
    -0.07
    POSITIVE LOGITS
    一�
    0.08
     осуществ
    0.07
     Humanity
    0.07
    ACE
    0.07
     measured
    0.07
     NON
    0.07
     activating
    0.07
    agn
    0.06
    ach
    0.06
     initiating
    0.06
    Act Density 0.003%

    No Known Activations