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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     usage
    -0.07
     bef
    -0.07
     rival
    -0.07
     Hasan
    -0.06
    	valid
    -0.06
    .va
    -0.06
    very
    -0.06
    bef
    -0.06
     worst
    -0.06
    POSITIVE LOGITS
     through
    0.16
     Through
    0.15
    through
    0.13
    Through
    0.13
     THROUGH
    0.12
     thru
    0.10
    _through
    0.09
    -through
    0.09
     durch
    0.08
     attravers
    0.08
    Act Density 0.056%

    No Known Activations