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

    Neuronpedia

    INDEX
    Explanations

    propose, call, host, hoard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Österreich
    0.47
     Kroger
    0.46
    rossover
    0.46
    ,":
    0.45
    غا
    0.45
    ”:
    0.45
     együtt
    0.44
    СР
    0.44
     Unterstützung
    0.44
     Ländern
    0.44
    POSITIVE LOGITS
    Drink
    0.48
     setelah
    0.48
     Cev
    0.46
    Belt
    0.45
    ல்
    0.45
     toro
    0.45
     eat
    0.44
     crc
    0.43
    Latency
    0.42
    ools
    0.42
    Act Density 0.003%

    No Known Activations