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

    Neuronpedia

    INDEX
    Explanations

    therapist finder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कने
    0.79
    ]+=
    0.76
     Crafted
    0.73
     partage
    0.73
    屶
    0.71
    梶
    0.70
    囵
    0.70
    公主
    0.70
    żu
    0.69
     compartido
    0.68
    POSITIVE LOGITS
    ther
    0.83
    Wed
    0.81
     Ter
    0.81
     ter
    0.74
     Wed
    0.73
    Ne
    0.72
     रै
    0.71
     Dem
    0.71
     Ur
    0.70
    Ū
    0.70
    Act Density 0.005%

    No Known Activations