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

    Neuronpedia

    INDEX
    Explanations

    physical access required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tenant
    0.46
    Normal
    0.45
     renta
    0.45
    T
    0.45
    n
    0.44
    وراق
    0.43
    ضای
    0.43
    Rel
    0.43
    Unit
    0.42
     drob
    0.42
    POSITIVE LOGITS
     അവളുടെ
    0.49
     గ్రహ
    0.47
    ücklich
    0.46
    の内
    0.46
     සං
    0.44
     భారతదేశ
    0.44
     మూడు
    0.44
     blames
    0.43
    untz
    0.43
     వ్యవస్థ
    0.43
    Act Density 0.001%

    No Known Activations