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

    Neuronpedia

    INDEX
    Explanations

    continue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stk
    -0.07
     woo
    -0.07
     ax
    -0.07
     ppt
    -0.07
     bigger
    -0.06
     Bingo
    -0.06
     outspoken
    -0.06
    IAM
    -0.06
     encounters
    -0.06
    relevant
    -0.06
    POSITIVE LOGITS
     continue
    0.09
     continued
    0.09
    	End
    0.08
    继
    0.07
     continuing
    0.07
     chatt
    0.07
     сколько
    0.07
    (typeof
    0.07
    "+"
    0.06
    .submit
    0.06
    Act Density 0.032%

    No Known Activations