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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cur
    -0.07
     phishing
    -0.07
    _Metadata
    -0.06
     Linkedin
    -0.06
    440
    -0.06
    üyordu
    -0.06
    [y
    -0.06
     včetně
    -0.06
     imaginable
    -0.06
    .invalid
    -0.06
    POSITIVE LOGITS
     cane
    0.08
     prowess
    0.06
    _fc
    0.06
    ียบ
    0.06
    ánd
    0.06
    weed
    0.06
     unic
    0.06
    _cond
    0.06
     quand
    0.06
     电
    0.06
    Act Density 0.540%

    No Known Activations