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

    Neuronpedia

    INDEX
    Explanations

    crystal caves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     operandSize
    0.60
    𝜁
    0.55
    acariy
    0.54
     permettent
    0.54
     ደረጃ
    0.52
     arrivent
    0.52
     შეს
    0.51
     gradioApp
    0.50
     añadi
    0.50
     adecuados
    0.50
    POSITIVE LOGITS
    ↵↵
    0.52
    zogen
    0.52
    ,
    0.46
    ↵
    0.46
    -
    0.46
    н
    0.46
    ه
    0.45
     Mó
    0.45
    !
    0.44
    ig
    0.43
    Act Density 0.000%

    No Known Activations