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

    Neuronpedia

    INDEX
    Explanations

    change of state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्याख्या
    0.37
    繫
    0.37
    Chain
    0.37
     الجما
    0.37
     Function
    0.35
     /
    0.35
     Cam
    0.35
     बोल
    0.35
     የታ
    0.34
    atum
    0.34
    POSITIVE LOGITS
     rojo
    0.44
     rouge
    0.44
     roja
    0.44
     wacky
    0.43
     diventare
    0.42
     devenir
    0.41
     convertirse
    0.41
     elsewhere
    0.40
     away
    0.39
    lemb
    0.39
    Act Density 0.012%

    No Known Activations