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

    Neuronpedia

    INDEX
    Explanations

    never followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    1.29
     it
    1.28
    وا
    1.25
    یم
    1.20
    ،
    1.16
    هم
    1.13
    மாக
    1.12
    ă
    1.12
     arbres
    1.11
     propres
    1.10
    POSITIVE LOGITS
    ↵
    1.55
    h
    1.43
     (
    1.10
    to
    1.01
    da
    0.98
    DATABASE
    0.91
     Transportation
    0.89
     Department
    0.86
    SI
    0.85
    ız
    0.85
    Act Density 0.060%

    No Known Activations