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

    Neuronpedia

    INDEX
    Explanations

    hashtags and color codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gica
    0.45
    »),
    0.43
    .(\
    0.41
    »)
    0.40
     weeping
    0.39
    »،
    0.38
    铒
    0.38
    箬
    0.38
     franchisees
    0.38
     nieruch
    0.37
    POSITIVE LOGITS
     #
    0.69
    #
    0.63
     SP
    0.59
    SP
    0.51
     '#
    0.51
    #
    0.50
    ##
    0.48
     `#
    0.47
    .#
    0.45
    ,#
    0.44
    Act Density 0.000%

    No Known Activations