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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tel
    -0.07
     Π
    -0.07
     How
    -0.06
     Distributed
    -0.06
    identified
    -0.06
     Healthy
    -0.06
     SetProperty
    -0.06
     uveden
    -0.06
     education
    -0.06
     votre
    -0.06
    POSITIVE LOGITS
     tela
    0.07
     meno
    0.06
    ;$
    0.06
    mět
    0.06
     malaysia
    0.06
     captain
    0.06
     mange
    0.06
    _CURRENT
    0.06
     empowerment
    0.06
     shorts
    0.06
    Act Density 0.008%

    No Known Activations