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

    Neuronpedia

    INDEX
    Explanations

    to supply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    marco
    0.54
     يت
    0.54
     construido
    0.54
    ميل
    0.53
    esquerda
    0.51
    tom
    0.51
    direito
    0.51
    تباين
    0.51
    beweg
    0.50
    sprach
    0.50
    POSITIVE LOGITS
    o
    0.52
     এব
    0.51
    தை
    0.51
     अलंकार
    0.49
     literary
    0.48
    राधना
    0.48
     shrine
    0.48
    تی
    0.47
     Shaikh
    0.47
     enchanting
    0.46
    Act Density 0.000%

    No Known Activations