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

    Neuronpedia

    INDEX
    Explanations

    ms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    需求
    -0.07
     پش
    -0.07
     Nevada
    -0.07
    :"-"`↵
    -0.07
     ath
    -0.06
    ังม
    -0.06
    Draft
    -0.06
     ATH
    -0.06
     PM
    -0.06
    .Schema
    -0.06
    POSITIVE LOGITS
    (all
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
     پوش
    0.06
     زیست
    0.06
    альний
    0.06
    �
    0.06
    _Success
    0.06
     fract
    0.06
     tartış
    0.06
    ertino
    0.06
    Act Density 0.036%

    No Known Activations