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
     herhangi
    -0.07
     smarty
    -0.07
    /link
    -0.06
    .phase
    -0.06
    science
    -0.06
    /scripts
    -0.06
    _monitor
    -0.06
    üstü
    -0.06
     Kin
    -0.06
    .simple
    -0.06
    POSITIVE LOGITS
     Seoul
    0.07
    授
    0.07
    won
    0.06
    Plant
    0.06
     meant
    0.06
     mệnh
    0.06
     lighting
    0.06
     ENG
    0.06
    iller
    0.06
    phia
    0.06
    Act Density 0.339%

    No Known Activations