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

    Neuronpedia

    INDEX
    Explanations

    Trigger and horizontal input parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posals
    0.40
    YSIS
    0.40
    谨慎
    0.40
    ODES
    0.40
    cmml
    0.38
    ेस
    0.38
    धाना
    0.37
    следования
    0.37
    MethodBeat
    0.36
    ribution
    0.35
    POSITIVE LOGITS
     parameter
    0.76
     Parameter
    0.65
    parameter
    0.62
     parameters
    0.61
     Parameters
    0.61
     parametr
    0.59
     parametri
    0.58
     parâmetros
    0.57
     parámetro
    0.55
    Parameter
    0.54
    Act Density 0.001%

    No Known Activations