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

    Neuronpedia

    INDEX
    Explanations

    fear itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    룺
    0.36
     tutorial
    0.35
     naphthalene
    0.35
     zależ
    0.35
    مارات
    0.34
    كنولوج
    0.34
    ائل
    0.33
     locom
    0.32
     aer
    0.32
     solos
    0.32
    POSITIVE LOGITS
    REVIEW
    0.42
     REVIEW
    0.39
     interesantes
    0.39
    EDIT
    0.39
     disappointed
    0.39
     Audiobook
    0.39
     Excelente
    0.38
    Shi
    0.38
    Gu
    0.37
     Audible
    0.37
    Act Density 0.001%

    No Known Activations