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

    Neuronpedia

    INDEX
    Explanations

    I understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ate
    0.50
    u
    0.47
                 
    0.41
     』
    0.40
    adik
    0.39
    ing
    0.38
    es
    0.38
    undance
    0.38
    ビニ
    0.38
     scenic
    0.38
    POSITIVE LOGITS
    اك
    0.51
    احة
    0.51
     wykon
    0.49
    Ofer
    0.49
    ავ
    0.47
     Besitz
    0.47
     Folgen
    0.46
     trato
    0.45
     condiciones
    0.45
    只要
    0.45
    Act Density 0.001%

    No Known Activations