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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enames
    -0.07
     보면
    -0.06
    정이
    -0.06
    алы
    -0.06
    	document
    -0.06
    _Tick
    -0.06
     자기
    -0.06
     erro
    -0.06
    (inflater
    -0.06
    	xtype
    -0.06
    POSITIVE LOGITS
    itet
    0.07
    —"
    0.07
    ůvodu
    0.06
    μενο
    0.06
    _AD
    0.06
     bombed
    0.06
    碰
    0.06
    films
    0.06
     появи
    0.06
     looph
    0.06
    Act Density 0.063%

    No Known Activations