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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eliminate
    -0.07
     caution
    -0.07
     trader
    -0.06
    enemy
    -0.06
    271
    -0.06
     examines
    -0.06
    inka
    -0.06
     guess
    -0.06
    .optimizer
    -0.06
    aml
    -0.06
    POSITIVE LOGITS
    �
    0.09
    �
    0.08
    �
    0.07
    食品
    0.07
    �
    0.07
    \
    0.07
     Scient
    0.07
     AJAX
    0.06
    更加
    0.06
    -
    0.06
    Act Density 0.012%

    No Known Activations