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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     limit
    -0.07
     enchant
    -0.07
    .diag
    -0.06
    	mask
    -0.06
     processing
    -0.06
     Numeric
    -0.06
    [it
    -0.06
     Pediatric
    -0.06
    .NewRequest
    -0.06
     filmm
    -0.06
    POSITIVE LOGITS
     spect
    0.07
     silver
    0.07
    BL
    0.06
    .Diagnostics
    0.06
    Об
    0.06
    REFER
    0.06
    Silver
    0.06
     этим
    0.06
    zipcode
    0.06
     byt
    0.06
    Act Density 0.213%

    No Known Activations