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

    Neuronpedia

    INDEX
    Explanations

    Dol module explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    followlike
    0.41
     Andy
    0.41
     ван
    0.41
     SARS
    0.39
     Vanessa
    0.39
     سا
    0.38
    salaryfrom
    0.38
    SARS
    0.37
    ochlor
    0.37
    Andy
    0.36
    POSITIVE LOGITS
    Dol
    0.52
     Dol
    0.51
     dol
    0.47
    TT
    0.41
    module
    0.38
    DOL
    0.38
    vic
    0.37
     DOL
    0.37
     Module
    0.36
     Val
    0.36
    Act Density 0.006%

    No Known Activations