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

    Neuronpedia

    INDEX
    Explanations

    Believe you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    醾
    0.29
    ਾਲ
    0.29
     allocation
    0.27
     Umbrella
    0.27
    Allocation
    0.27
    <0x94>
    0.27
    нэт
    0.27
     प्रतिनिधित्व
    0.27
     XRD
    0.27
     symbolTable
    0.27
    POSITIVE LOGITS
    Gon
    0.30
    J
    0.29
    gon
    0.29
    GON
    0.29
    So
    0.28
    ON
    0.28
    sequ
    0.28
     Mathemat
    0.27
    boy
    0.26
    cle
    0.25
    Act Density 0.000%

    No Known Activations