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

    Neuronpedia

    INDEX
    Explanations

    undeciphered scripts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruitment
    0.47
    oint
    0.45
    Support
    0.41
    parency
    0.41
    وروب
    0.41
     最后
    0.41
    利
    0.41
    Attrib
    0.40
    }}/
    0.40
     mandib
    0.40
    POSITIVE LOGITS
     disse
    0.48
     reins
    0.42
     doskona
    0.42
     mercur
    0.41
     Gil
    0.41
     sprink
    0.41
     excellent
    0.41
     Thomas
    0.40
     declara
    0.39
     Dutton
    0.39
    Act Density 0.000%

    No Known Activations