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

    Neuronpedia

    INDEX
    Explanations

    error handling and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Integrante
    0.35
    细胞
    0.35
    esehen
    0.34
    Saludo
    0.34
     細胞
    0.33
    ेडियम
    0.32
    Celltype
    0.32
    GoObject
    0.31
    เซล
    0.31
    efois
    0.31
    POSITIVE LOGITS
    4
    0.37
     and
    0.36
     Configuration
    0.34
     configuration
    0.33
    5
    0.33
     Assuming
    0.32
    3
    0.32
     (
    0.31
     Let
    0.31
     haven
    0.31
    Act Density 0.566%

    No Known Activations