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

    Neuronpedia

    INDEX
    Explanations

    Cloud infrastructure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forfe
    -0.07
     cohort
    -0.07
     Sunday
    -0.07
     surtout
    -0.07
     привы
    -0.07
     horrend
    -0.06
     vừa
    -0.06
     генера
    -0.06
     epid
    -0.06
     판
    -0.06
    POSITIVE LOGITS
    STYLE
    0.07
    van
    0.07
    SENS
    0.07
    敌
    0.06
    .onResume
    0.06
    560
    0.06
     lider
    0.06
    commend
    0.06
     Br
    0.06
    sten
    0.06
    Act Density 0.001%

    No Known Activations