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

    Neuronpedia

    INDEX
    Explanations

    ' or * followed by numbers/letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.38
    。
    0.30
    ."
    0.27
    ↵↵↵
    0.27
    ።
    0.26
    .”
    0.26
    ".
    0.26
    ។
    0.25
     ។
    0.25
    }$.
    0.24
    POSITIVE LOGITS
     Instead
    0.33
     Unlike
    0.33
    Unlike
    0.27
     During
    0.27
     Firstly
    0.26
     While
    0.26
     Although
    0.25
     It
    0.25
     Öncelikle
    0.25
     In
    0.25
    Act Density 1.009%

    No Known Activations