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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cont
    -0.07
    veh
    -0.06
    lik
    -0.06
    -forward
    -0.06
    Launcher
    -0.06
    ’ll
    -0.06
     �
    -0.06
    vey
    -0.06
    Doc
    -0.06
     Sing
    -0.06
    POSITIVE LOGITS
     heterosexual
    0.07
    pecial
    0.06
    .relu
    0.06
     autorelease
    0.06
    .FileNotFoundException
    0.06
    ;]/
    0.06
    чис
    0.06
    .panelControl
    0.06
    /oauth
    0.06
     Aleks
    0.06
    Act Density 0.067%

    No Known Activations