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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dresser
    -0.07
     '|'
    -0.07
    ptype
    -0.07
    .***
    -0.07
     particle
    -0.06
    손
    -0.06
    spoken
    -0.06
    okes
    -0.06
    682
    -0.06
     fracture
    -0.06
    POSITIVE LOGITS
    xeb
    0.07
    	val
    0.06
     rarity
    0.06
    alarında
    0.06
    autical
    0.06
    .minLength
    0.06
    statt
    0.06
    abin
    0.06
    lsru
    0.06
     Fay
    0.06
    Act Density 0.012%

    No Known Activations