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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osc
    -0.07
    历
    -0.07
    OTOR
    -0.07
    glob
    -0.06
    تين
    -0.06
     ie
    -0.06
     TKey
    -0.06
     mourn
    -0.06
    +/
    -0.06
    (egt
    -0.06
    POSITIVE LOGITS
     Friedrich
    0.08
    正确的
    0.07
    삠
    0.07
    Recording
    0.07
    _simulation
    0.07
    	required
    0.07
     remedies
    0.07
     RU
    0.07
     Ram
    0.07
     Reply
    0.07
    Act Density 0.002%

    No Known Activations