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

    Neuronpedia

    INDEX
    Explanations

    mind, cognition, thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.25
    ل
    1.15
    dat
    1.13
    ма
    1.02
    ig
    1.01
    issements
    0.93
    dirs
    0.93
    dt
    0.92
    ade
    0.91
    dan
    0.91
    POSITIVE LOGITS
    ;
    1.38
    N
    1.30
     mind
    1.23
    DF
    1.13
    CH
    1.09
    CE
    1.07
     אחד
    1.06
     Sekolah
    1.05
    B
    1.05
    E
    1.03
    Act Density 0.030%

    No Known Activations