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
     NHS
    -0.07
     myster
    -0.07
     records
    -0.07
     wonders
    -0.06
    ъек
    -0.06
    ウィ
    -0.06
    .NEW
    -0.06
    ampus
    -0.06
     flock
    -0.06
     faz
    -0.06
    POSITIVE LOGITS
    eu
    0.06
    =session
    0.06
    reon
    0.06
    Framework
    0.06
    -value
    0.06
    .addObserver
    0.06
     naw
    0.05
     gep
    0.05
     měsíců
    0.05
    upakan
    0.05
    Act Density 0.029%

    No Known Activations