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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tue
    -0.07
    isté
    -0.07
     Ca
    -0.06
     acesso
    -0.06
     Kath
    -0.06
    _svc
    -0.06
    ою
    -0.06
     LM
    -0.06
    404
    -0.06
    _startup
    -0.06
    POSITIVE LOGITS
    *scale
    0.07
    _campaign
    0.06
    _G
    0.06
    .requires
    0.06
     mel
    0.06
     الصن
    0.06
    =batch
    0.06
     ماده
    0.05
     deprivation
    0.05
    .rotation
    0.05
    Act Density 0.044%

    No Known Activations