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

    Neuronpedia

    INDEX
    Explanations

    managing, needing, or using functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éticos
    0.41
    Poppins
    0.40
     చి
    0.38
     וב
    0.38
    reetings
    0.38
    uretics
    0.38
    LogError
    0.38
    ikin
    0.38
    ilación
    0.38
    iguing
    0.37
    POSITIVE LOGITS
    expensive
    0.44
     expensive
    0.43
     manage
    0.43
     strung
    0.40
     contener
    0.40
    manage
    0.39
     brauchen
    0.39
     habt
    0.39
     đòi
    0.39
     gestionar
    0.39
    Act Density 0.015%

    No Known Activations