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

    Neuronpedia

    INDEX
    Explanations

    clipboard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Archive
    -0.08
     anticipation
    -0.08
     bailout
    -0.08
    Interpolation
    -0.08
     sociedades
    -0.08
     estate
    -0.07
    步
    -0.07
     interoperability
    -0.07
     refugee
    -0.07
     interpolate
    -0.07
    POSITIVE LOGITS
     Flush
    0.08
     installé
    0.08
     Drink
    0.08
     installiert
    0.08
     toen
    0.08
     설치
    0.08
     Install
    0.08
     Jung
    0.07
     Rose
    0.07
     Freud
    0.07
    Act Density 0.002%

    No Known Activations