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

    Neuronpedia

    INDEX
    Explanations

    `http`, `spotify`, `tls`, `Job`, `cipher`, `cpu`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.25
    他
    1.20
    ၇
    1.18
    ίας
    1.12
    ими
    1.09
    बर्ग
    1.08
    ங்களையும்
    1.02
    ن
    1.02
    응
    1.01
    ை
    1.00
    POSITIVE LOGITS
    ta
    1.19
     riport
    1.10
     contenant
    1.10
    D
    1.09
    ti
    1.06
     coli
    1.05
    guards
    1.03
    screw
    1.02
    ]'
    1.02
     tourn
    1.01
    Act Density 0.000%

    No Known Activations