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

    Neuronpedia

    INDEX
    Explanations

    Rin, drugs, BPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ره
    0.49
    fixing
    0.49
    一
    0.47
    姦
    0.46
    ్రీన్
    0.46
     Fixing
    0.46
    agine
    0.45
    tLogRow
    0.45
    Agriculture
    0.45
    鐗
    0.45
    POSITIVE LOGITS
     in
    0.50
     permitan
    0.48
    nées
    0.45
     sosok
    0.45
    ങ്ങനെ
    0.43
    на
    0.43
    ரின்
    0.42
     purport
    0.42
     múltiples
    0.41
    <0xAC>
    0.41
    Act Density 0.000%

    No Known Activations