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

    Neuronpedia

    INDEX
    Explanations

    code snippets indicating line numbers in files

    oai_token-act-pair · gemini-2.0-flash

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.68
     femininas
    -0.62
     Мексичка
    -0.61
     BorderRadius
    -0.61
    GEBURTSDATUM
    -0.59
    zzleHttp
    -0.57
    msgTypes
    -0.56
     noires
    -0.56
    WithIOException
    -0.56
    +#+#
    -0.55
    POSITIVE LOGITS
    phosphat
    0.48
     no
    0.47
     constat
    0.46
    addOn
    0.43
    perror
    0.43
    sauce
    0.43
    折
    0.43
     случа
    0.43
    ظ
    0.43
    ikkert
    0.42
    Act Density 0.245%

    No Known Activations