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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stial
    -0.07
     �
    -0.06
    П
    -0.06
     Dit
    -0.06
     желез
    -0.06
    \model
    -0.06
    calc
    -0.06
     deadliest
    -0.06
    >alert
    -0.06
     Pul
    -0.06
    POSITIVE LOGITS
    Comment
    0.07
     argues
    0.07
     occupational
    0.06
     critiques
    0.06
    ーズ
    0.06
    (notification
    0.06
    TouchUpInside
    0.06
    -note
    0.06
    Env
    0.06
     invalidate
    0.06
    Act Density 0.007%

    No Known Activations