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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uppen
    -0.07
     blunt
    -0.07
    _comments
    -0.07
     supplementary
    -0.07
    cılık
    -0.07
    .getSize
    -0.07
     eros
    -0.06
     rotate
    -0.06
    ().'/
    -0.06
    -arm
    -0.06
    POSITIVE LOGITS
    超过
    0.07
     Không
    0.07
     timestamp
    0.06
    vir
    0.06
    /notification
    0.06
    在国外
    0.06
    车展
    0.06
    gone
    0.06
    懈
    0.06
    mostat
    0.06
    Act Density 0.362%

    No Known Activations