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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     না
    -0.08
     заранее
    -0.07
     ন
    -0.07
     সম
    -0.07
    IZER
    -0.07
     Prem
    -0.07
     образователь
    -0.07
     Teile
    -0.07
     unnecessarily
    -0.07
     bestehen
    -0.07
    POSITIVE LOGITS
    Completed
    0.11
     conclu
    0.10
    completed
    0.10
     completes
    0.10
     completed
    0.10
     heals
    0.09
     healed
    0.09
     tamam
    0.09
     abgeschlossen
    0.09
    _completed
    0.09
    Act Density 0.002%

    No Known Activations