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

    Neuronpedia

    INDEX
    Explanations

    synonyms and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tears
    0.56
    t
    0.47
    تص
    0.46
    ودي
    0.45
     Arsen
    0.44
    rockets
    0.44
    sound
    0.43
    source
    0.43
    ỡng
    0.43
    determine
    0.43
    POSITIVE LOGITS
     гэта
    0.49
     dusky
    0.47
     volunteering
    0.46
     PROFESSIONAL
    0.44
     volunte
    0.42
     peque
    0.42
     ๆ
    0.42
     cybersecurity
    0.42
     зокрема
    0.41
     CIM
    0.41
    Act Density 0.000%

    No Known Activations