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

    Neuronpedia

    INDEX
    Explanations

    prompts asking me for details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    klär
    0.77
    rown
    0.73
    Есть
    0.72
    ෝජ
    0.72
    জনের
    0.72
     comprender
    0.71
     तरी
    0.71
     diciendo
    0.70
     hinsichtlich
    0.69
    ausal
    0.69
    POSITIVE LOGITS
     SPL
    0.83
    একটি
    0.79
    ńsk
    0.75
    codec
    0.75
     بعض
    0.74
     dígitos
    0.73
     Styled
    0.73
    它的
    0.72
     depósito
    0.72
    odesk
    0.71
    Act Density 0.082%

    No Known Activations