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

    Neuronpedia

    INDEX
    Explanations

    completely inappropriate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불구하고
    0.95
    toon
    0.92
    mith
    0.82
    fontein
    0.80
    tas
    0.78
    <0x80>
    0.75
    afe
    0.75
    toc
    0.75
    ":
    0.74
     specialist
    0.74
    POSITIVE LOGITS
     semblance
    0.97
     abscess
    0.93
     вовсе
    0.91
     escult
    0.91
     cubierta
    0.91
     \'
    0.89
    朐
    0.89
     faux
    0.89
    '}}
    0.88
    >
    0.88
    Act Density 0.000%

    No Known Activations