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

    Neuronpedia

    INDEX
    Explanations

    Technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Capture
    -0.07
     instances
    -0.06
    前の
    -0.06
     cheaper
    -0.06
     mnohem
    -0.06
     dziew
    -0.06
    ят
    -0.06
    	foreach
    -0.06
     coat
    -0.06
    .vector
    -0.06
    POSITIVE LOGITS
    іття
    0.07
     ult
    0.06
    UNIT
    0.06
    .’
    0.06
    calc
    0.06
     mildly
    0.06
    �
    0.06
    ,“
    0.06
    _TD
    0.06
    )++;↵
    0.06
    Act Density 0.091%

    No Known Activations