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

    Neuronpedia

    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NOW
    -0.08
    XYZ
    -0.08
    RAL
    -0.07
    冯
    -0.07
     ll
    -0.07
     dentro
    -0.07
    _MANY
    -0.07
    	List
    -0.07
     subscribed
    -0.07
    view
    -0.07
    POSITIVE LOGITS
    맄
    0.08
     bullshit
    0.07
    ɜ
    0.07
     مما
    0.07
    Utility
    0.07
     ousted
    0.07
    多样化
    0.07
     Courier
    0.07
    *r
    0.07
    ˂
    0.07
    Act Density 0.017%

    No Known Activations