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

    Neuronpedia

    INDEX
    Explanations

    risk and danger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acements
    -0.07
    •
    -0.07
     compagn
    -0.07
     vacation
    -0.06
    -С
    -0.06
     Logistic
    -0.06
    amics
    -0.06
    лег
    -0.06
    ckill
    -0.06
    Reporting
    -0.06
    POSITIVE LOGITS
     attracted
    0.07
    _actions
    0.07
     outr
    0.07
    .removeListener
    0.07
    ・━
    0.06
    dater
    0.06
    anda
    0.06
    /up
    0.06
     рекоменда
    0.06
    subnet
    0.06
    Act Density 0.010%

    No Known Activations