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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    groups
    -0.07
     imbalance
    -0.06
     admitted
    -0.06
    ppers
    -0.06
     cihaz
    -0.06
    oice
    -0.06
    occ
    -0.06
     royal
    -0.06
    ंस
    -0.06
     gia
    -0.06
    POSITIVE LOGITS
    ічної
    0.06
    ActionTypes
    0.06
     exceptionally
    0.06
    _rq
    0.06
     REALLY
    0.06
     таке
    0.06
     Specs
    0.06
     Leads
    0.06
     erectile
    0.06
     �
    0.06
    Act Density 0.088%

    No Known Activations