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

    Neuronpedia

    INDEX
    Explanations

    Ptr, eta, Month, right, AS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.07
    mathrm
    0.85
    um
    0.84
    support
    0.80
    ru
    0.76
    gmail
    0.76
    n
    0.76
    money
    0.76
    e
    0.75
    brand
    0.75
    POSITIVE LOGITS
     són
    0.96
     inaccurate
    0.80
    よび
    0.80
     efflux
    0.78
     incompetence
    0.78
     montrent
    0.77
    ńska
    0.77
     sono
    0.76
     inhum
    0.76
     đến
    0.75
    Act Density 0.000%

    No Known Activations