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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obligations
    -0.07
     Heroes
    -0.06
    IsNull
    -0.06
     CONTROL
    -0.06
    اث
    -0.06
    /authentication
    -0.06
     optimizations
    -0.06
     rush
    -0.06
    IFIED
    -0.06
    entence
    -0.06
    POSITIVE LOGITS
    øre
    0.07
    Não
    0.07
     Een
    0.07
     não
    0.07
     Düz
    0.06
    ][_
    0.06
    pod
    0.06
     خود
    0.06
    ΙΔ
    0.06
    ็นการ
    0.06
    Act Density 0.082%

    No Known Activations