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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scanner
    -0.07
    .Modified
    -0.07
     Walk
    -0.07
    _hal
    -0.06
    んと
    -0.06
     낮
    -0.06
     некотор
    -0.06
     csr
    -0.06
    ูก
    -0.06
     pathname
    -0.06
    POSITIVE LOGITS
    (Response
    0.08
     cancers
    0.07
    )){↵
    0.06
     Docker
    0.06
    直播
    0.06
    ै,
    0.06
    ."'
    0.06
    .onerror
    0.06
     querying
    0.06
    ..
    0.06
    Act Density 0.014%

    No Known Activations