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

    Neuronpedia

    INDEX
    Explanations

    that means, that suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.49
    A
    0.43
    Z
    0.42
    L
    0.42
    H
    0.40
    ים
    0.39
    E
    0.39
    in
    0.39
    us
    0.38
    as
    0.38
    POSITIVE LOGITS
    zelfde
    0.66
     pesky
    0.60
     fateful
    0.44
     particular
    0.39
     rarest
    0.36
     same
    0.36
     ćete
    0.34
    ляма
    0.34
     particolare
    0.33
    ]+"
    0.33
    Act Density 0.031%

    No Known Activations