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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তল
    0.36
     reflectance
    0.36
     کھانا
    0.36
    ligare
    0.36
     competitively
    0.35
     лест
    0.35
     kuin
    0.34
     toen
    0.34
     पुण्य
    0.34
     focussed
    0.33
    POSITIVE LOGITS
    asd
    0.46
    5
    0.39
     treads
    0.38
    9
    0.38
    abcd
    0.37
     abc
    0.36
    #$%
    0.36
    8
    0.36
    椃
    0.36
     секу
    0.36
    Act Density 0.036%

    No Known Activations