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

    Neuronpedia

    INDEX
    Explanations

    image sensors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goodbye
    -0.08
     Goodbye
    -0.08
    rego
    -0.08
     detach
    -0.08
     desfr
    -0.08
    'ins
    -0.07
     farewell
    -0.07
    namespace
    -0.07
    ’ins
    -0.07
     Advisor
    -0.07
    POSITIVE LOGITS
     madre
    0.09
    leine
    0.09
     maternal
    0.08
     gating
    0.08
     mujer
    0.08
     NAND
    0.08
     cellulose
    0.08
     BASIS
    0.08
     ನಿವಾಸ
    0.08
     gated
    0.08
    Act Density 0.003%

    No Known Activations