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

    Neuronpedia

    INDEX
    Explanations

    Roses are red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    植物
    0.40
     RESP
    0.36
    VD
    0.36
     годом
    0.35
     Hayes
    0.35
    黴
    0.35
     Congress
    0.34
    CSF
    0.34
    ρίες
    0.33
     дли
    0.33
    POSITIVE LOGITS
     ornamentation
    0.43
    ight
    0.42
     naughty
    0.41
     obnoxious
    0.41
     ornate
    0.41
    專
    0.40
     Namen
    0.40
     sweet
    0.40
    נען
    0.39
    🤫
    0.39
    Act Density 0.000%

    No Known Activations