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

    Neuronpedia

    INDEX
    Explanations

    fuzzy, blunt, brute force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unicate
    0.43
    防火
    0.39
    Fluent
    0.39
    ￢
    0.38
    플레이
    0.38
    Cond
    0.36
    condensation
    0.36
    ≻
    0.36
    excell
    0.36
    イク
    0.35
    POSITIVE LOGITS
    kus
    0.47
     IO
    0.47
     brute
    0.46
     brutal
    0.45
     brutally
    0.44
     force
    0.43
     Boyer
    0.43
     kus
    0.42
     blunt
    0.41
     forcing
    0.40
    Act Density 0.005%

    No Known Activations