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

    Neuronpedia

    INDEX
    Explanations

    Researchers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /provider
    -0.07
     eviction
    -0.06
    隔
    -0.06
    غيل
    -0.06
    ยา
    -0.06
    id
    -0.06
     scoop
    -0.06
    view
    -0.06
     Bolton
    -0.06
    30
    -0.06
    POSITIVE LOGITS
     researchers
    0.09
    memiş
    0.08
    ataset
    0.07
     RC
    0.07
     researcher
    0.07
     Redis
    0.07
    Researchers
    0.07
     getTime
    0.07
    muş
    0.07
    žit
    0.07
    Act Density 0.012%

    No Known Activations