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

    Neuronpedia

    INDEX
    Explanations

    potential or affinity for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isotropic
    1.28
    ir
    1.21
    ্বক
    1.20
    Derivative
    1.18
     всего
    1.14
    derivative
    1.13
    दृ
    1.12
    opharm
    1.12
    কম
    1.11
    lapse
    1.10
    POSITIVE LOGITS
     true
    1.14
     mia
    1.02
     minst
    1.02
     vida
    0.97
     cardiaque
    0.96
     leis
    0.96
     tournaments
    0.92
     Koi
    0.90
     cola
    0.90
     wife
    0.90
    Act Density 0.000%

    No Known Activations