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

    Neuronpedia

    INDEX
    Explanations

    complex strategic reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    決して
    0.42
    慓
    0.41
    0.41
     comien
    0.40
    ⓞ
    0.40
     computerized
    0.39
    !“
    0.39
    하였습니다
    0.38
    ำ
    0.38
    ํ
    0.38
    POSITIVE LOGITS
     nihil
    0.70
     entropy
    0.67
     cognitive
    0.66
     fractal
    0.64
     epistem
    0.63
     bullshit
    0.62
     existential
    0.61
     absur
    0.60
     fucked
    0.60
     Bayesian
    0.59
    Act Density 0.050%

    No Known Activations