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

    Neuronpedia

    INDEX
    Explanations

    home and relationships

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿಯಾಗಿ
    0.71
     Priya
    0.70
    csrf
    0.68
    CSR
    0.68
    诌
    0.66
    nesia
    0.64
     ].
    0.64
     CSR
    0.64
    axies
    0.64
     Guggenheim
    0.64
    POSITIVE LOGITS
     preparando
    0.63
    Fluid
    0.54
    טי
    0.53
    家庭
    0.53
    🧼
    0.53
     facendo
    0.52
    採
    0.52
    ::~
    0.52
     selepas
    0.52
    実践
    0.52
    Act Density 0.000%

    No Known Activations