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

    Neuronpedia

    INDEX
    Explanations

    how worn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하실
    0.43
     decomp
    0.42
     simulating
    0.42
     показа
    0.41
    =")"
    0.41
     overw
    0.41
    હિ
    0.41
    l
    0.41
    ба
    0.40
     confused
    0.40
    POSITIVE LOGITS
     tarafından
    0.48
    valuer
    0.48
     Havel
    0.48
     yakni
    0.46
    entiti
    0.46
     et
    0.44
    ண்ட
    0.44
    èm
    0.44
    śmy
    0.44
     solche
    0.43
    Act Density 0.001%

    No Known Activations