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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ould
    -0.07
    协商
    -0.07
    Prince
    -0.06
    也没
    -0.06
    addOn
    -0.06
    tid
    -0.06
    getType
    -0.06
     conducts
    -0.06
     rob
    -0.06
    ainen
    -0.06
    POSITIVE LOGITS
     Scalar
    0.08
     zam
    0.07
     Lös
    0.07
     strpos
    0.07
     ł
    0.06
     legalized
    0.06
    .Lo
    0.06
     tôn
    0.06
     Substitute
    0.06
     Liberal
    0.06
    Act Density 0.001%

    No Known Activations