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

    Neuronpedia

    INDEX
    Explanations

    show cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Object
    -0.06
     plotted
    -0.06
    	len
    -0.06
     waves
    -0.06
    RA
    -0.06
    ね
    -0.06
     dump
    -0.06
    ffen
    -0.06
    _write
    -0.06
    OUNT
    -0.06
    POSITIVE LOGITS
    _portfolio
    0.06
    _compute
    0.06
    stadt
    0.06
     padre
    0.06
     dost
    0.06
    라피
    0.06
    halb
    0.06
    スコ
    0.06
     everywhere
    0.06
    "class
    0.06
    Act Density 0.012%

    No Known Activations