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

    Neuronpedia

    INDEX
    Explanations

    breakdown of cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ating
    0.40
     laughter
    0.40
     ..........
    0.38
     აღ
    0.38
    dinga
    0.37
     mass
    0.36
    laughter
    0.36
    jumpa
    0.36
    fa
    0.35
    ammak
    0.35
    POSITIVE LOGITS
    อป
    0.43
     Geschwindigkeit
    0.43
    ⧐
    0.40
     personas
    0.40
    casted
    0.38
     सोशल
    0.37
    FFF
    0.37
     ሜ
    0.37
     Greene
    0.37
     Dav
    0.36
    Act Density 0.000%

    No Known Activations