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

    Neuronpedia

    INDEX
    Explanations

    wife and she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xC2>
    0.43
    .
    0.42
     and
    0.38
     🥰
    0.36
     July
    0.36
     hat
    0.36
     violated
    0.35
     rage
    0.35
    <b>
    0.34
    ,
    0.34
    POSITIVE LOGITS
    pośred
    0.45
     मींस
    0.45
    മ്ബ
    0.44
    FieldSet
    0.42
     செயல்பா
    0.42
    >∕
    0.41
    睃
    0.40
    regen
    0.40
    nije
    0.40
    )^{*}$
    0.40
    Act Density 0.000%

    No Known Activations