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

    Neuronpedia

    INDEX
    Explanations

    '

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    склад
    -0.07
    .PLAIN
    -0.07
     aber
    -0.06
    variant
    -0.06
     pounding
    -0.06
     selber
    -0.06
     खड
    -0.06
     indefinitely
    -0.06
    .But
    -0.06
    수를
    -0.06
    POSITIVE LOGITS
    _components
    0.07
    OUCH
    0.07
     searchable
    0.06
    HX
    0.06
    WI
    0.06
    asha
    0.06
     ==↵
    0.06
     порт
    0.06
     donors
    0.06
     Strawberry
    0.06
    Act Density 0.000%

    No Known Activations