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

    Neuronpedia

    INDEX
    Explanations

    introduces answer or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Также
    0.39
    什么是
    0.36
     Также
    0.36
    ）、
    0.35
     Kxd
    0.34
     /(\
    0.34
    ᡵ
    0.34
    但也
    0.33
     والخ
    0.33
    也能
    0.32
    POSITIVE LOGITS
     Well
    0.98
    Well
    0.84
     well
    0.83
     Answer
    0.75
    well
    0.73
     Basically
    0.72
     WELL
    0.71
     basically
    0.70
     Mainly
    0.70
     answer
    0.69
    Act Density 0.022%

    No Known Activations