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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LRV
    -0.07
     Hawk
    -0.06
    _ab
    -0.06
    laps
    -0.06
    _IND
    -0.06
    phans
    -0.06
     промислов
    -0.06
     rosa
    -0.06
     COURT
    -0.06
     Scrap
    -0.06
    POSITIVE LOGITS
    していた
    0.08
     wildlife
    0.07
     страх
    0.06
    /tinyos
    0.06
     Donetsk
    0.06
     фунда
    0.06
    abilité
    0.06
     федераль
    0.06
    の中
    0.06
     randomized
    0.06
    Act Density 0.000%

    No Known Activations