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

    Neuronpedia

    INDEX
    Explanations

    references to nightlife, eating out, and drinking, along with related verbs

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.51
    AxisAlignment
    -0.50
    NameInMap
    -0.48
     habrá
    -0.47
    AddTagHelper
    -0.47
     Olímp
    -0.46
     طريق
    -0.45
     jumps
    -0.45
    hoga
    -0.45
     стри
    -0.44
    POSITIVE LOGITS
     out
    1.77
     Out
    1.45
    out
    1.38
    Out
    1.35
     OUT
    1.25
    OUT
    1.16
    outs
    1.11
     outs
    1.11
    アウト
    0.95
     keluar
    0.91
    Act Density 0.605%

    No Known Activations