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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     غر
    -0.06
    Monitoring
    -0.06
     Gow
    -0.06
    -master
    -0.06
    ّ
    -0.06
    KM
    -0.06
    .storage
    -0.06
    _WRAPPER
    -0.06
     اخلاق
    -0.05
     Sharks
    -0.05
    POSITIVE LOGITS
     Ül
    0.07
    (cat
    0.07
    드로
    0.07
    _PER
    0.06
     babes
    0.06
     vez
    0.06
     calend
    0.06
    ]+
    0.06
    Das
    0.06
     Alleg
    0.06
    Act Density 0.000%

    No Known Activations