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

    Neuronpedia

    INDEX
    Explanations

    facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opia
    -0.07
     populations
    -0.07
    _levels
    -0.06
     embroid
    -0.06
     walks
    -0.06
     inadvertently
    -0.06
     peoples
    -0.06
    _Arg
    -0.06
     covariance
    -0.06
     enthusiasts
    -0.06
    POSITIVE LOGITS
    URL
    0.07
    .removeClass
    0.07
    nested
    0.06
     athletic
    0.06
    如下
    0.06
    atisf
    0.06
     наст
    0.06
    Carrier
    0.06
    exclude
    0.06
     Sext
    0.06
    Act Density 0.006%

    No Known Activations