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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Muller
    0.81
    اديم
    0.80
    ❻
    0.77
     Müller
    0.76
     [%
    0.75
    ينية
    0.75
    zym
    0.74
    ᵕ
    0.72
    विड
    0.71
    ၈
    0.71
    POSITIVE LOGITS
     festivities
    0.87
     anniversary
    0.79
    覦
    0.78
     fraternity
    0.76
     terrace
    0.74
    targeted
    0.73
     الترم
    0.73
     tarafından
    0.72
    我对
    0.72
    amese
    0.71
    Act Density 0.005%

    No Known Activations