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

    Neuronpedia

    INDEX
    Explanations

    long RAM, skills, prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Safety
    0.36
    ',$
    0.36
    interpret
    0.35
    MOR
    0.35
     Morales
    0.34
    हार
    0.34
     selfie
    0.34
     skincare
    0.34
    žila
    0.34
    蕴
    0.34
    POSITIVE LOGITS
    ционными
    0.44
     eggs
    0.40
    قلال
    0.40
     obliqu
    0.39
     пенсии
    0.39
     omp
    0.39
    нди
    0.38
     अंडे
    0.38
    ឡ
    0.38
    쟁
    0.38
    Act Density 0.000%

    No Known Activations