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

    Neuronpedia

    INDEX
    Explanations

    best of the best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consultation
    0.43
     Consultation
    0.42
     Fak
    0.40
     relied
    0.39
     consultations
    0.38
     bothered
    0.38
    גם
    0.38
     ур
    0.37
     notorious
    0.37
     Cermak
    0.36
    POSITIVE LOGITS
    dyž
    0.42
    啊
    0.40
     éprou
    0.39
    AutoScale
    0.39
     freezed
    0.39
    OPER
    0.38
    डाउन
    0.38
    ახ
    0.38
    ۔۔۔۔
    0.38
    ICPSR
    0.38
    Act Density 0.000%

    No Known Activations