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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plasma
    -0.06
    it
    -0.06
    /widget
    -0.06
    VERTEX
    -0.06
     sav
    -0.06
    .skip
    -0.06
     liqu
    -0.06
    _Pin
    -0.06
     serge
    -0.06
    ..
    -0.06
    POSITIVE LOGITS
     IDENT
    0.07
    ائج
    0.07
     الشي
    0.07
    prix
    0.06
    (D
    0.06
    计
    0.06
    iento
    0.06
    soon
    0.06
    lds
    0.06
    ewood
    0.06
    Act Density 0.026%

    No Known Activations