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

    Neuronpedia

    INDEX
    Explanations

    code, variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     celebrates
    -0.07
    ############################################################################
    -0.07
     Cater
    -0.07
     Seeds
    -0.07
     челов
    -0.07
     CLOCK
    -0.07
    卻
    -0.06
    -console
    -0.06
     confl
    -0.06
     pada
    -0.06
    POSITIVE LOGITS
    ()));
    0.07
     aller
    0.06
    탈
    0.06
     limbs
    0.06
     conductivity
    0.06
    .balance
    0.06
    terminal
    0.06
    _visual
    0.06
    .priv
    0.06
     pozor
    0.06
    Act Density 0.000%

    No Known Activations