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

    Neuronpedia

    INDEX
    Explanations

    automate outbound emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    resultados
    0.53
    quando
    0.46
    ળો
    0.45
    veu
    0.45
     mentales
    0.45
     Есть
    0.44
    cuando
    0.44
     independencia
    0.42
     únicas
    0.42
    oules
    0.42
    POSITIVE LOGITS
     Platinum
    0.52
    Platinum
    0.42
    dB
    0.41
     Fabric
    0.40
    仕組み
    0.38
     adequate
    0.38
     tkan
    0.38
    xF
    0.38
    Fabric
    0.38
    取り組み
    0.38
    Act Density 0.009%

    No Known Activations