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

    Neuronpedia

    INDEX
    Explanations

    01

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -spinner
    -0.07
    -points
    -0.07
     aluminium
    -0.07
    pet
    -0.07
    .TRAN
    -0.06
    -elect
    -0.06
     squares
    -0.06
    ايي
    -0.06
    lamp
    -0.06
     reverence
    -0.06
    POSITIVE LOGITS
     сильно
    0.06
     @$_
    0.06
    键
    0.06
     Charts
    0.06
     arising
    0.06
     rejo
    0.06
     errorMessage
    0.06
     Result
    0.06
    seudo
    0.06
    glas
    0.06
    Act Density 0.009%

    No Known Activations