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

    Neuronpedia

    INDEX
    Explanations

    response to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    czne
    1.85
    ajā
    1.84
    MENTS
    1.76
    ע
    1.69
    ۰
    1.66
    NAME
    1.64
    Millions
    1.64
     dní
    1.63
    Когда
    1.61
    MAPb
    1.60
    POSITIVE LOGITS
    scaping
    1.45
     isn
    1.45
    शाली
    1.42
    м
    1.41
    <0xA7>
    1.40
    ays
    1.38
    <0x99>
    1.36
    та
    1.35
    ﻧ
    1.34
    notch
    1.29
    Act Density 0.000%

    No Known Activations