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

    Neuronpedia

    INDEX
    Explanations

    idiomatic phrases and slang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瑄
    0.46
    📶
    0.46
    Density
    0.46
     licensure
    0.46
     متعلق
    0.44
     idk
    0.44
    💻
    0.43
    🎮
    0.43
    诶
    0.43
    🧠
    0.43
    POSITIVE LOGITS
     envisaged
    0.82
     dodgy
    0.71
     bloke
    0.68
     appalling
    0.67
     rubbish
    0.64
     lads
    0.64
     orientated
    0.60
     envisage
    0.60
     flog
    0.59
     hugely
    0.59
    Act Density 0.010%

    No Known Activations