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

    Neuronpedia

    INDEX
    Explanations

    pointer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coc
    -0.08
     correspondent
    -0.07
     Domain
    -0.07
    氛围
    -0.07
     edição
    -0.07
    ден
    -0.07
     phases
    -0.07
    奋进
    -0.07
     giữa
    -0.06
    藝
    -0.06
    POSITIVE LOGITS
     WebSocket
    0.07
    .fil
    0.07
    ი
    0.07
    _TYPED
    0.07
    ANCELED
    0.07
     disabling
    0.07
     Padres
    0.07
    雳
    0.07
    وش
    0.07
     Brun
    0.07
    Act Density 0.001%

    No Known Activations