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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Это
    -0.06
    Ag
    -0.06
     руковод
    -0.06
    _PARAMS
    -0.06
     плот
    -0.06
    .*
    -0.06
    .streaming
    -0.06
    OTT
    -0.06
    /t
    -0.06
    :UIControlState
    -0.06
    POSITIVE LOGITS
     axs
    0.07
    contador
    0.07
    endment
    0.07
     hip
    0.06
    	Label
    0.06
     injecting
    0.06
     Rockies
    0.06
    τας
    0.06
    (ord
    0.06
    Truth
    0.06
    Act Density 0.025%

    No Known Activations