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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ける
    -0.08
    ?");↵
    -0.07
    alien
    -0.07
    emplates
    -0.07
    altern
    -0.07
     stre
    -0.07
     virtues
    -0.06
    uto
    -0.06
     refs
    -0.06
    alie
    -0.06
    POSITIVE LOGITS
    維
    0.06
    IRON
    0.06
    нт
    0.06
    脂
    0.06
     seizing
    0.06
     casually
    0.06
     Lindsey
    0.06
    EFAULT
    0.06
    mysqli
    0.06
    036
    0.06
    Act Density 0.000%

    No Known Activations