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

    Neuronpedia

    INDEX
    Explanations

    field names or database columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intestino
    0.25
     sustancias
    0.24
    కున్న
    0.24
    வ்வளவு
    0.23
     अल्कोहल
    0.23
     toată
    0.23
    வ்வாறு
    0.23
     abrazo
    0.23
     bhfuil
    0.23
     nuovamente
    0.23
    POSITIVE LOGITS
    /
    0.36
    es
    0.30
    _
    0.30
    .
    0.29
     της
    0.27
    -
    0.27
     ቦ
    0.26
    er
    0.25
     โดย
    0.25
    ,
    0.25
    Act Density 0.236%

    No Known Activations