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

    Neuronpedia

    INDEX
    Explanations

    FILES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhal
    -0.06
     Pune
    -0.06
    >*</
    -0.06
     kı
    -0.06
    _S
    -0.06
    -li
    -0.06
     Wales
    -0.06
    _AV
    -0.06
     Пів
    -0.06
     Benjamin
    -0.06
    POSITIVE LOGITS
    FILES
    0.15
     fruity
    0.11
     busty
    0.10
    top
    0.08
    SESSION
    0.07
     smoothly
    0.07
     Heb
    0.07
    .session
    0.07
     sexist
    0.07
     supportive
    0.06
    Act Density 0.003%

    No Known Activations