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

    Neuronpedia

    INDEX
    Explanations

    alternative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HEAD
    -0.07
     �
    -0.06
    (JSONObject
    -0.06
     خواب
    -0.06
    啦
    -0.06
    誉
    -0.06
    _lit
    -0.06
     dismal
    -0.06
     speak
    -0.06
    azer
    -0.06
    POSITIVE LOGITS
     Alternative
    0.10
     alternative
    0.10
    Alternative
    0.10
    alternative
    0.09
     romant
    0.07
     Challenger
    0.07
     alien
    0.07
    _altern
    0.07
     alternatives
    0.07
    -P
    0.07
    Act Density 0.005%

    No Known Activations