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
    imesteps
    -0.07
     explore
    -0.07
    (String
    -0.06
     Для
    -0.06
    328
    -0.06
     Hipp
    -0.06
    fp
    -0.06
    ließlich
    -0.06
     Sym
    -0.06
     FBI
    -0.06
    POSITIVE LOGITS
    .REACT
    0.07
     potency
    0.07
     Truly
    0.07
     caption
    0.06
     روان
    0.06
    OutOf
    0.06
     Finds
    0.06
     stray
    0.06
     Hồng
    0.06
    ูงส
    0.06
    Act Density 0.005%

    No Known Activations