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

    Neuronpedia

    INDEX
    Explanations

    Gala / Partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intrad
    0.57
     ergonomic
    0.57
     perros
    0.56
     koi
    0.55
     incense
    0.55
     filosofía
    0.54
     seja
    0.54
     perro
    0.54
     esempl
    0.53
     perto
    0.53
    POSITIVE LOGITS
    Partners
    0.59
    Partner
    0.55
    Ex
    0.55
    Reg
    0.54
     Partners
    0.54
    Κα
    0.53
    Friend
    0.52
    :^(
    0.52
    下列
    0.52
    Zach
    0.52
    Act Density 0.070%

    No Known Activations