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

    Neuronpedia

    INDEX
    Explanations

    pain and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    坚
    0.45
    卫生
    0.44
    শিয়া
    0.44
     Conservation
    0.44
    无线
    0.43
    分组
    0.43
    纺
    0.42
     профилакти
    0.42
    常见
    0.42
    льной
    0.42
    POSITIVE LOGITS
     psychosis
    0.55
     predicate
    0.53
     mafia
    0.52
     latent
    0.51
     gangster
    0.50
     amyloid
    0.49
     gangsters
    0.49
     frauen
    0.48
     wares
    0.48
     precepts
    0.48
    Act Density 0.043%

    No Known Activations