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

    Neuronpedia

    INDEX
    Explanations

    shell script commands and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRAS
    0.44
    avez
    0.40
    পুল
    0.39
    Routes
    0.38
    NAM
    0.37
    oum
    0.36
    зів
    0.36
    nam
    0.36
    📥
    0.36
    पने
    0.35
    POSITIVE LOGITS
     álgebra
    0.39
     sixteenth
    0.36
    nested
    0.36
    ālā
    0.36
    쑹
    0.36
     fourteenth
    0.35
     अंधे
    0.35
     mammalian
    0.35
     Willy
    0.35
    ומ
    0.34
    Act Density 0.000%

    No Known Activations