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

    Neuronpedia

    INDEX
    Explanations

    prepositions linking phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.49
    ే
    0.47
    K
    0.43
    J
    0.43
    Q
    0.41
    ა
    0.41
    G
    0.41
    Z
    0.41
    D
    0.40
    B
    0.39
    POSITIVE LOGITS
    \
    0.49
     to
    0.48
    (
    0.42
     was
    0.41
     is
    0.38
     (
    0.38
    -
    0.37
    いて
    0.36
     it
    0.35
    ного
    0.35
    Act Density 7.062%

    No Known Activations