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

    Neuronpedia

    INDEX
    Explanations

    negative consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     руки
    -0.07
     mực
    -0.07
    .resources
    -0.07
    .rect
    -0.07
     parliament
    -0.07
     helpless
    -0.07
     tủ
    -0.06
    lication
    -0.06
    coef
    -0.06
     Deputy
    -0.06
    POSITIVE LOGITS
    aggregate
    0.06
    IntPtr
    0.06
     Deployment
    0.06
    _not
    0.06
     HinderedRotor
    0.06
    _endpoint
    0.06
    填
    0.05
    _XDECREF
    0.05
     lục
    0.05
    Portfolio
    0.05
    Act Density 0.114%

    No Known Activations