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

    Neuronpedia

    INDEX
    Explanations

    enables or causes outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.35
    ۔
    0.31
    ।
    0.29
    *.
    0.28
    :
    0.28
    >.
    0.26
    》。
    0.26
    '.
    0.26
    .
    0.26
    ።
    0.25
    POSITIVE LOGITS
     makes
    0.53
     ensures
    0.47
     enables
    0.44
     helps
    0.44
     gives
    0.43
     allows
    0.42
     provides
    0.40
     adds
    0.40
     zorgt
    0.40
     creates
    0.40
    Act Density 1.752%

    No Known Activations