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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DIG
    -0.07
    廊
    -0.07
    AGON
    -0.07
     generosity
    -0.07
     trois
    -0.07
    tensor
    -0.07
     conclude
    -0.07
    -split
    -0.07
    agon
    -0.07
     Gulf
    -0.06
    POSITIVE LOGITS
    452
    0.06
    751
    0.06
    ً
    0.06
     toplam
    0.05
     replicate
    0.05
    \E
    0.05
    _eps
    0.05
     cigars
    0.05
    ै↵
    0.05
    (",")↵
    0.05
    Act Density 0.011%

    No Known Activations