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

    Neuronpedia

    INDEX
    Explanations

    harmful/illegal activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -d
    -0.07
     svůj
    -0.06
     Conduct
    -0.06
    _more
    -0.06
    ّة
    -0.06
    coeff
    -0.06
    ým
    -0.06
    _META
    -0.06
     Logistic
    -0.06
    /H
    -0.06
    POSITIVE LOGITS
    <Class
    0.06
    aintenance
    0.06
    _marker
    0.06
    ลล
    0.06
     processed
    0.06
     persuasive
    0.06
     DRIVE
    0.06
    INDER
    0.06
     Citadel
    0.06
    (Image
    0.06
    Act Density 0.029%

    No Known Activations