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

    Neuronpedia

    INDEX
    Explanations

    Not the same as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hugs
    0.49
    archiv
    0.47
     Able
    0.46
     arch
    0.45
     sok
    0.45
    Aus
    0.44
     Erkennt
    0.44
     Einstellung
    0.43
    ಆ
    0.43
    癥
    0.43
    POSITIVE LOGITS
    isu
    0.53
    ição
    0.52
    nonce
    0.52
    চ্ছ
    0.48
    uge
    0.47
    ous
    0.47
    iese
    0.46
    )\\
    0.46
    iesen
    0.45
    ímica
    0.45
    Act Density 0.001%

    No Known Activations