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

    Neuronpedia

    INDEX
    Explanations

    Decimals in math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eld
    -0.09
    _resources
    -0.08
     Recursos
    -0.08
    Ä
    -0.08
     Ressourcen
    -0.08
     Resources
    -0.08
     Jared
    -0.08
    .resources
    -0.08
    .uns
    -0.08
    _neighbors
    -0.08
    POSITIVE LOGITS
     upper
    0.08
     sexu
    0.07
     nedenle
    0.07
     uga
    0.07
     threshold
    0.07
     genital
    0.07
    ுகளை
    0.07
    ையாக
    0.07
     seksual
    0.07
     voile
    0.07
    Act Density 0.051%

    No Known Activations