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

    Neuronpedia

    INDEX
    Explanations

    projection welding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.71
    𝑬
    0.68
     některé
    0.64
     Когда
    0.61
    mprj
    0.60
     comenta
    0.60
    h
    0.60
     ለመ
    0.59
    совой
    0.59
     Kern
    0.59
    POSITIVE LOGITS
     billionaires
    0.61
    تها
    0.60
     fist
    0.58
     tennis
    0.52
     bullion
    0.52
    irl
    0.51
     histogram
    0.51
     fair
    0.50
    יי
    0.50
     gaz
    0.50
    Act Density 0.000%

    No Known Activations