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

    Neuronpedia

    INDEX
    Explanations

    hour no one knows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heute
    0.55
     bugün
    0.55
     tumeur
    0.53
     implique
    0.53
     terres
    0.50
    Como
    0.50
     gioi
    0.50
     frau
    0.50
     be
    0.49
     señora
    0.49
    POSITIVE LOGITS
     入り
    0.52
    agon
    0.51
    buster
    0.51
    evan
    0.49
    anko
    0.49
    thisStudent
    0.48
     Witcher
    0.48
    idential
    0.47
    buddy
    0.46
     Sasuke
    0.46
    Act Density 0.000%

    No Known Activations