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

    Neuronpedia

    INDEX
    Explanations

    intense physical distress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дека
    -0.08
     nằm
    -0.07
    ผม
    -0.07
    ]++;↵
    -0.07
     мне
    -0.06
     subtitles
    -0.06
     связ
    -0.06
    >>>(
    -0.06
     SPE
    -0.06
    准备
    -0.06
    POSITIVE LOGITS
     shave
    0.07
    mamış
    0.07
    -model
    0.06
    講
    0.06
     handleError
    0.06
    likely
    0.06
    :'',
    0.06
     conformity
    0.06
    _weights
    0.06
    ardash
    0.06
    Act Density 0.070%

    No Known Activations