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

    Neuronpedia

    INDEX
    Explanations

    crime and theft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convi
    0.40
    ствие
    0.39
     erad
    0.38
     barges
    0.36
     fórmula
    0.36
     форму
    0.35
     regra
    0.35
     vaisseaux
    0.34
     обре
    0.34
    стя
    0.34
    POSITIVE LOGITS
     Objective
    0.38
     Using
    0.35
    Objective
    0.35
    sciences
    0.35
    Abstract
    0.34
    GST
    0.34
    itime
    0.33
    S
    0.33
    Android
    0.33
    Using
    0.32
    Act Density 0.000%

    No Known Activations