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

    Neuronpedia

    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ROM
    -0.07
    -metadata
    -0.07
     contraseña
    -0.07
    phon
    -0.06
     Anton
    -0.06
     मई
    -0.06
     ó
    -0.06
    (sim
    -0.06
    τος
    -0.06
    _CALC
    -0.06
    POSITIVE LOGITS
    ней
    0.07
     superheroes
    0.06
     fallback
    0.06
    ام
    0.06
     PROFILE
    0.06
     Hawai
    0.06
    ABI
    0.06
     Goodman
    0.06
    Leaks
    0.06
     acab
    0.05
    Act Density 0.000%

    No Known Activations