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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _published
    -0.06
     CLIENT
    -0.06
     K
    -0.06
     Hunter
    -0.06
     remover
    -0.06
     práci
    -0.06
     Conversation
    -0.05
    StorageSync
    -0.05
     whiskey
    -0.05
    ровать
    -0.05
    POSITIVE LOGITS
    	org
    0.08
    utral
    0.07
    私は
    0.07
     trotz
    0.07
    Unlike
    0.07
     leftover
    0.07
    .ie
    0.07
    석
    0.07
    	str
    0.07
     genu
    0.07
    Act Density 0.026%

    No Known Activations