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

    Neuronpedia

    INDEX
    Explanations

    clauses, commercial, German

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Percentage
    0.47
    Percentage
    0.45
    percentage
    0.45
     Worked
    0.42
    ictive
    0.41
     Guru
    0.41
     answered
    0.41
    answered
    0.40
     ctrl
    0.39
    hdad
    0.39
    POSITIVE LOGITS
    менов
    0.37
     دوم
    0.37
     domains
    0.36
    始めて
    0.35
    DC
    0.35
    IFY
    0.35
     "${
    0.34
     Scenic
    0.34
    ococ
    0.34
     components
    0.33
    Act Density 0.000%

    No Known Activations