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

    Neuronpedia

    INDEX
    Explanations

    Internet text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centerpiece
    -0.06
     вважа
    -0.06
     食
    -0.06
    .userInfo
    -0.06
    ्मच
    -0.06
     �
    -0.06
     ark
    -0.06
    Ч
    -0.06
    ;:;:
    -0.06
    /************************************************************************************************
    -0.06
    POSITIVE LOGITS
    _digit
    0.08
     Základní
    0.07
     mell
    0.07
    Power
    0.06
    jde
    0.06
    ojí
    0.06
    (vars
    0.06
    cadena
    0.06
    ================
    0.06
    abr
    0.06
    Act Density 0.000%

    No Known Activations