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

    Neuronpedia

    INDEX
    Explanations

    php or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Daniel
    0.81
     millilit
    0.80
    forter
    0.78
    ലുള്ള
    0.77
    textepsilon
    0.75
    Une
    0.75
     Jako
    0.74
     انگلیسی
    0.74
     सेकेंड
    0.73
    Ook
    0.72
    POSITIVE LOGITS
    ↵
    0.92
    ↵↵
    0.89
    <0x0D>
    0.80
     }
    0.76
     declare
    0.71
     suicides
    0.68
     exit
    0.67
    παν
    0.64
     //-->
    0.62
    ↵↵↵
    0.62
    Act Density 0.000%

    No Known Activations