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

    Neuronpedia

    INDEX
    Explanations

    punctuation and no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaining
    -0.07
    _day
    -0.06
    unfold
    -0.06
     lottery
    -0.06
     }).
    -0.05
     judgement
    -0.05
    	let
    -0.05
    explained
    -0.05
    าของ
    -0.05
     tumblr
    -0.05
    POSITIVE LOGITS
    λμ
    0.08
     Moines
    0.07
     väl
    0.07
    imers
    0.07
     Ör
    0.07
    .prof
    0.07
     mun
    0.06
     vaše
    0.06
    _Core
    0.06
     SYS
    0.06
    Act Density 0.001%

    No Known Activations