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

    Neuronpedia

    INDEX
    Explanations

    ent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    らしい
    -0.08
    levels
    -0.07
     project
    -0.07
    มากกว
    -0.07
    279
    -0.07
    quares
    -0.06
     kolem
    -0.06
     reprodu
    -0.06
     aggreg
    -0.06
     dalších
    -0.06
    POSITIVE LOGITS
     silent
    0.15
     Silent
    0.15
     silently
    0.11
    silent
    0.10
     silence
    0.10
     Silence
    0.09
     silenced
    0.07
    	INNER
    0.07
     facilitate
    0.07
    斷
    0.07
    Act Density 0.003%

    No Known Activations