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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پیش
    -0.07
    کش
    -0.07
     jeans
    -0.07
    _EDGE
    -0.07
     permanent
    -0.06
    だけど
    -0.06
     inherits
    -0.06
     Ripple
    -0.06
     Ree
    -0.06
    지가
    -0.06
    POSITIVE LOGITS
     qualifies
    0.07
    .format
    0.07
     repeating
    0.06
    áte
    0.06
     spokeswoman
    0.06
     impact
    0.06
     khoản
    0.06
    -best
    0.06
     firmy
    0.06
     Console
    0.06
    Act Density 0.006%

    No Known Activations