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

    Neuronpedia

    INDEX
    Explanations

    block diagram

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prefs
    1.29
    rax
    1.24
     imprend
    1.23
    RELATIVA
    1.23
     pathophysiology
    1.19
     informazioni
    1.17
     flound
    1.17
     депута
    1.16
     facendo
    1.16
    ্ধু
    1.16
    POSITIVE LOGITS
    of
    0.96
    Đối
    0.91
    .}$
    0.87
    ために
    0.85
    ಿಂದ
    0.84
     خالص
    0.83
    Carmen
    0.83
     amyg
    0.83
     Haiti
    0.83
     Carthage
    0.82
    Act Density 0.000%

    No Known Activations