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

    Neuronpedia

    INDEX
    Explanations

    gift ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .extension
    -0.07
     еп
    -0.06
    ึ
    -0.06
    现代
    -0.06
     Merr
    -0.06
    '])?
    -0.06
     Jah
    -0.06
    .Kind
    -0.06
    Evt
    -0.06
     المؤ
    -0.06
    POSITIVE LOGITS
     decl
    0.06
     offending
    0.06
     starred
    0.06
    *self
    0.06
    anter
    0.06
    _DELTA
    0.06
    ::::::::
    0.06
    .Owner
    0.06
     designing
    0.06
     Defendant
    0.06
    Act Density 0.028%

    No Known Activations