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

    Neuronpedia

    INDEX
    Explanations

    discovery, science, research, breakthrough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    0.46
    ภัณฑ์
    0.41
    <unused31>
    0.41
    ostasis
    0.41
    ymmetries
    0.40
    含义
    0.40
    ટ્સ
    0.40
    ாளையம்
    0.40
    禕
    0.40
     Coates
    0.39
    POSITIVE LOGITS
    CF
    0.52
     clash
    0.45
     liquid
    0.44
    CG
    0.43
    סט
    0.43
    ?),
    0.42
    ED
    0.42
     किसी
    0.42
    Boa
    0.42
    sound
    0.41
    Act Density 0.000%

    No Known Activations