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

    Neuronpedia

    INDEX
    Explanations

    dictionary represented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chirurg
    0.48
     ennemis
    0.48
     genius
    0.47
     baseApiPath
    0.47
    vaegir
    0.47
     titleImageUrl
    0.47
     genet
    0.47
     douze
    0.46
     persuas
    0.46
     রাজ্যে
    0.45
    POSITIVE LOGITS
    (
    0.63
    E
    0.50
    M
    0.50
    म
    0.47
    Sight
    0.46
    I
    0.46
    R
    0.45
    O
    0.45
    Microsoft
    0.44
    .
    0.44
    Act Density 0.001%

    No Known Activations