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

    Neuronpedia

    INDEX
    Explanations

    the, your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mani
    -0.07
     BaseModel
    -0.07
    lander
    -0.07
     OMX
    -0.07
     Innoc
    -0.07
    <Token
    -0.07
     aba
    -0.06
     Winn
    -0.06
     sanity
    -0.06
     cute
    -0.06
    POSITIVE LOGITS
     """↵
    0.07
     başvur
    0.07
     Collections
    0.06
    (win
    0.06
    overe
    0.06
     рай
    0.06
     Default
    0.06
    untary
    0.06
    GNUC
    0.05
     call
    0.05
    Act Density 0.021%

    No Known Activations