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

    Neuronpedia

    INDEX
    Explanations

    product

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dicho
    -0.08
    _PUSH
    -0.07
     prevailing
    -0.07
    -layer
    -0.07
    rà
    -0.07
    'es
    -0.07
    民間
    -0.07
    ín
    -0.07
     elements
    -0.07
     wrought
    -0.06
    POSITIVE LOGITS
    爱好者
    0.07
     Recomm
    0.07
    ycling
    0.07
     Prospect
    0.07
     Torrent
    0.07
     Scandin
    0.07
    环境中
    0.07
    gradable
    0.07
     תוכנ
    0.07
    lernen
    0.07
    Act Density 0.011%

    No Known Activations