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

    Neuronpedia

    INDEX
    Explanations

    individual part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Babe
    0.49
     Bios
    0.48
     Reakt
    0.46
     Manch
    0.46
     Bol
    0.45
     gigante
    0.45
     Barg
    0.44
     printr
    0.44
        
    0.44
    …………..
    0.43
    POSITIVE LOGITS
    3
    0.54
    5
    0.51
    ৩৯
    0.50
    stage
    0.49
    1
    0.49
     commentators
    0.48
     differed
    0.48
    were
    0.48
    vocals
    0.47
    ijs
    0.47
    Act Density 0.000%

    No Known Activations