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

    Neuronpedia

    INDEX
    Explanations

    social media posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DC
    0.39
    PRO
    0.38
    OU
    0.38
    Ŏ
    0.37
    OC
    0.37
    TOG
    0.36
    *
    0.36
    PU
    0.36
    Discovery
    0.36
    TOM
    0.36
    POSITIVE LOGITS
     socialista
    0.40
     Appodeal
    0.36
     sinds
    0.36
     demethyl
    0.34
    reo
    0.34
    iphenyl
    0.33
    ').':
    0.33
    عة
    0.33
     Nauchno
    0.33
    MktCap
    0.33
    Act Density 0.005%

    No Known Activations