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

    Neuronpedia

    INDEX
    Explanations

    ///

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poz
    -0.08
     Gray
    -0.07
    риз
    -0.07
    ('"
    -0.07
     된다
    -0.07
     Damn
    -0.06
     aging
    -0.06
     Assad
    -0.06
    ad
    -0.06
     badass
    -0.06
    POSITIVE LOGITS
    便
    0.07
    ۲۰۰
    0.07
    Github
    0.07
    Pane
    0.06
    (term
    0.06
    .Sn
    0.06
     holistic
    0.06
     kendine
    0.06
     accordingly
    0.06
    .Application
    0.06
    Act Density 0.006%

    No Known Activations