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

    Neuronpedia

    INDEX
    Explanations

    ô

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     softer
    -0.07
    lication
    -0.06
     ONLINE
    -0.06
     melan
    -0.06
     Merch
    -0.06
    _matrices
    -0.06
    426
    -0.06
     seventeen
    -0.06
    -stream
    -0.06
    TERNAL
    -0.06
    POSITIVE LOGITS
     Gn
    0.08
     Nath
    0.08
    nul
    0.08
     gn
    0.08
    ner
    0.07
    agnar
    0.07
    nim
    0.07
     наг
    0.07
     Got
    0.07
     Nero
    0.07
    Act Density 0.044%

    No Known Activations