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

    Neuronpedia

    INDEX
    Explanations

    opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bespoke
    -0.07
    אביב
    -0.07
    定律
    -0.07
    -of
    -0.07
    лект
    -0.07
    _eval
    -0.07
    wg
    -0.07
    lbl
    -0.07
    称呼
    -0.06
    umn
    -0.06
    POSITIVE LOGITS
    (instruction
    0.08
     URI
    0.07
     organized
    0.07
     binaries
    0.07
    琉璃
    0.07
    .scrollView
    0.07
     brass
    0.07
     Origin
    0.07
    Friday
    0.07
     présence
    0.07
    Act Density 0.080%

    No Known Activations