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

    Neuronpedia

    INDEX
    Explanations

    words beginning with cat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     battaglia
    1.11
     polizia
    1.09
     supposing
    1.04
     impuestos
    1.00
    다면
    0.99
     deel
    0.96
    ัว
    0.94
     எதிர
    0.94
    esterol
    0.94
     ponctués
    0.93
    POSITIVE LOGITS
    agory
    1.30
    aclysm
    1.30
    gor
    1.08
    nip
    1.07
     земель
    0.97
    咪
    0.94
    Cedar
    0.93
    álogo
    0.92
    fantastic
    0.92
    ckpt
    0.92
    Act Density 0.084%

    No Known Activations