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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Add
    -0.07
     Boulder
    -0.07
    าของ
    -0.06
    byt
    -0.06
     Hughes
    -0.06
    Add
    -0.06
     lantern
    -0.06
    かない
    -0.06
     희
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     kept
    0.06
     extends
    0.06
    icable
    0.06
    -notification
    0.06
    spir
    0.06
    rey
    0.06
     SQLite
    0.06
    (prop
    0.06
     easy
    0.06
    ifice
    0.06
    Act Density 0.009%

    No Known Activations