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

    Neuronpedia

    INDEX
    Explanations

    relates to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lieben
    0.90
    EH
    0.89
    ূপে
    0.82
     वे
    0.82
    atak
    0.81
    they
    0.79
    TeV
    0.79
    ę
    0.78
     unglaublich
    0.78
    texto
    0.77
    POSITIVE LOGITS
     accumulates
    0.78
     correlates
    0.77
    ビリ
    0.76
     disputes
    0.75
     disciplines
    0.75
     Parses
    0.75
    の上
    0.74
     Keeps
    0.73
     bends
    0.72
     lectures
    0.71
    Act Density 0.000%

    No Known Activations