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

    Neuronpedia

    INDEX
    Explanations

    cans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pad
    -0.07
     dictated
    -0.07
     phase
    -0.07
    cripcion
    -0.07
    	S
    -0.06
    เตร
    -0.06
     backend
    -0.06
     route
    -0.06
    ursor
    -0.06
    ひ
    -0.06
    POSITIVE LOGITS
     cans
    0.13
     canned
    0.08
    snapshot
    0.06
     captivity
    0.06
     diminishing
    0.06
     unpleasant
    0.06
     shitty
    0.06
    redis
    0.06
     vX
    0.06
    (wx
    0.06
    Act Density 0.005%

    No Known Activations