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

    Neuronpedia

    INDEX
    Explanations

    ls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aches
    -0.09
                        ↵
    -0.08
    ادث
    -0.08
    ийн
    -0.07
     throughout
    -0.07
     Consent
    -0.07
     capacitación
    -0.07
     Bought
    -0.07
     sufr
    -0.07
     ד
    -0.07
    POSITIVE LOGITS
    目录
    0.10
    -directory
    0.10
     directory
    0.09
    (directory
    0.08
    listing
    0.08
    Directory
    0.08
    .listdir
    0.08
    Listing
    0.08
    _listing
    0.08
     wok
    0.08
    Act Density 0.003%

    No Known Activations