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

    Neuronpedia

    INDEX
    Explanations

    Mixing ingredients in a bowl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⌀
    0.40
    illos
    0.40
    焼き
    0.40
     sacrificio
    0.39
     Vapor
    0.38
     grid
    0.38
    HEAT
    0.38
    贴
    0.37
     огне
    0.37
     Flame
    0.37
    POSITIVE LOGITS
     mixer
    0.86
     mixers
    0.84
     Mixing
    0.77
     Mixer
    0.75
     mixing
    0.74
    Mixing
    0.74
    搅拌
    0.72
    mixer
    0.71
    mixing
    0.67
     stirred
    0.66
    Act Density 0.264%

    No Known Activations