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

    Neuronpedia

    INDEX
    Explanations

    admissions and entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -1.00
     submissions
    -0.97
     tartalomajánló
    -0.95
     intrusions
    -0.94
    isations
    -0.93
    writeField
    -0.92
     admissions
    -0.90
     contributions
    -0.90
     registrations
    -0.90
     nominations
    -0.90
    POSITIVE LOGITS
     made
    0.63
     from
    0.54
    ,
    0.51
     like
    0.47
     offent
    0.47
    .
    0.46
     liitty
    0.46
    angkut
    0.46
     that
    0.45
     prosedur
    0.45
    Act Density 0.033%

    No Known Activations