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

    Neuronpedia

    INDEX
    Explanations

    wheel malfunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autocomplete
    0.44
     Settlement
    0.41
     autocomplete
    0.39
    念念
    0.39
     moderation
    0.38
    చ్చే
    0.38
    뗄
    0.36
     prospects
    0.35
    荤
    0.35
     Fertility
    0.35
    POSITIVE LOGITS
    ar
    0.47
    platten
    0.41
     이
    0.41
    ment
    0.40
    sen
    0.40
    istiwa
    0.40
    arr
    0.39
    thinmathspace
    0.39
    ens
    0.39
    ement
    0.38
    Act Density 0.000%

    No Known Activations