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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cove
    -0.07
     dar
    -0.07
    ofile
    -0.07
    	self
    -0.06
    BA
    -0.06
    _tuple
    -0.06
    .npy
    -0.06
    first
    -0.06
    ิพ
    -0.06
    _FREE
    -0.06
    POSITIVE LOGITS
     t
    0.19
    ,t
    0.12
    t
    0.11
    =t
    0.09
    +t
    0.09
    [t
    0.09
    (t
    0.09
    (tt
    0.09
    )t
    0.09
    <t
    0.08
    Act Density 0.026%

    No Known Activations