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

    Neuronpedia

    INDEX
    Explanations

    Construction development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handling
    -0.07
    latent
    -0.06
     profitability
    -0.06
    kie
    -0.06
    -padding
    -0.06
    НА
    -0.06
    DA
    -0.06
    da
    -0.06
    male
    -0.06
    iterator
    -0.06
    POSITIVE LOGITS
    าตร
    0.07
     Embassy
    0.07
     самостоятельно
    0.07
    Spr
    0.06
    argv
    0.06
    _CHARACTER
    0.06
    aptors
    0.06
     laugh
    0.06
     Belmont
    0.06
     Fabric
    0.06
    Act Density 0.026%

    No Known Activations