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

    Neuronpedia

    INDEX
    Explanations

    ending "al"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Engineers
    -0.07
    _ssl
    -0.07
     cock
    -0.07
     moon
    -0.07
    .....
    -0.06
    witch
    -0.06
    تها
    -0.06
    ระเบ
    -0.06
     exc
    -0.06
     Strategy
    -0.06
    POSITIVE LOGITS
    al
    0.10
    AL
    0.10
    alf
    0.07
    ial
    0.07
     discredit
    0.07
    etal
    0.06
     χα
    0.06
    ал
    0.06
    ả
    0.06
    ười
    0.06
    Act Density 0.018%

    No Known Activations