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

    Neuronpedia

    INDEX
    Explanations

    Casual conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     해야
    -0.07
     loro
    -0.07
     nost
    -0.06
    けない
    -0.06
     степ
    -0.06
    -G
    -0.06
    (cid
    -0.06
    dao
    -0.06
     cocktail
    -0.06
     stakeholders
    -0.06
    POSITIVE LOGITS
    :no
    0.07
     perseverance
    0.07
     consume
    0.07
     Todd
    0.06
     relating
    0.06
    olkata
    0.06
    /business
    0.06
    -you
    0.06
    ...)
    0.06
     Redskins
    0.06
    Act Density 0.115%

    No Known Activations