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

    Neuronpedia

    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     العق
    -0.07
    .Abstract
    -0.06
    paralleled
    -0.06
     confidentiality
    -0.06
     queried
    -0.06
     Depos
    -0.06
     Mou
    -0.06
     questioned
    -0.06
     STDOUT
    -0.06
     Intelligence
    -0.06
    POSITIVE LOGITS
    533
    0.07
    下载
    0.07
     cảm
    0.07
    石
    0.07
    :class
    0.06
     наб
    0.06
     přeb
    0.06
    (reason
    0.06
    andelier
    0.06
    .lift
    0.06
    Act Density 0.021%

    No Known Activations