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

    Neuronpedia

    INDEX
    Explanations

    meaning and identity

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mouth
    0.53
    ingles
    0.52
     shelter
    0.52
    grayscale
    0.52
    drunk
    0.52
     nameless
    0.52
    ங்களிலிருந்து
    0.51
    keygen
    0.51
    brushes
    0.51
    quil
    0.50
    POSITIVE LOGITS
     рођено
    0.63
    urusan
    0.62
    uiscono
    0.61
     DESIGN
    0.60
     بس
    0.59
     opro
    0.59
    لاه
    0.59
     Hussain
    0.58
     imaju
    0.58
     디자인
    0.57
    Act Density 0.000%

    No Known Activations