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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yles
    -0.07
    .roll
    -0.06
     supervisors
    -0.06
     контра
    -0.06
    γκό
    -0.06
     walk
    -0.06
     dakika
    -0.06
    chnitt
    -0.06
    روض
    -0.06
    -enter
    -0.06
    POSITIVE LOGITS
     EXISTS
    0.07
     accordance
    0.06
    )?↵
    0.06
    .PackageManager
    0.06
     indication
    0.06
    	req
    0.06
    ensitivity
    0.06
    Checks
    0.06
     yana
    0.06
     cadastr
    0.06
    Act Density 0.060%

    No Known Activations