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

    Neuronpedia

    INDEX
    Explanations

    ugly in negative prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ΝΑ
    0.41
    relli
    0.41
    Subview
    0.40
    participants
    0.38
    棪
    0.38
    zám
    0.37
    𒈬
    0.37
     세율
    0.37
    łem
    0.37
    ायती
    0.37
    POSITIVE LOGITS
    రుగులు
    0.35
    ِب
    0.35
     central
    0.35
     satisfacción
    0.34
     grueso
    0.34
     Bibli
    0.34
    .»
    0.34
     ты
    0.34
     Fine
    0.34
     cozy
    0.33
    Act Density 0.001%

    No Known Activations