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

    Neuronpedia

    INDEX
    Explanations

    model from model compile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बाघ
    0.42
     beginnetje
    0.40
     chamb
    0.40
    эння
    0.40
     disf
    0.39
     Resolutions
    0.38
    ogène
    0.38
    íoch
    0.38
    ธาร
    0.37
    inputText
    0.36
    POSITIVE LOGITS
    de
    0.44
    6
    0.41
    bo
    0.38
    k
    0.38
    κ
    0.38
    cb
    0.38
    up
    0.37
    cac
    0.37
    pra
    0.37
    દ
    0.37
    Act Density 0.000%

    No Known Activations