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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    óż
    -0.08
     mojo
    -0.08
     cục
    -0.07
     styled
    -0.07
     tandem
    -0.07
    CCI
    -0.07
    결
    -0.06
    .uid
    -0.06
    \a
    -0.06
     Girlfriend
    -0.06
    POSITIVE LOGITS
     allowable
    0.07
     Ever
    0.07
    CEEDED
    0.06
    Е
    0.06
    E
    0.06
     ();↵↵
    0.06
     Amer
    0.06
    edb
    0.06
     equitable
    0.06
     Nicolas
    0.06
    Act Density 0.016%

    No Known Activations