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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setHorizontalGroup
    -0.08
    人为
    -0.07
    Pictures
    -0.07
     Necklace
    -0.07
    änner
    -0.07
    帅哥
    -0.07
    vo
    -0.07
    념
    -0.07
    祀
    -0.07
    税
    -0.07
    POSITIVE LOGITS
    ANO
    0.08
    ˵
    0.07
    (plot
    0.07
    .are
    0.07
    atem
    0.07
    ACHED
    0.06
    �
    0.06
    ebileceği
    0.06
     waterproof
    0.06
    REF
    0.06
    Act Density 0.025%

    No Known Activations