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

    Neuronpedia

    INDEX
    Explanations

    experiences and memories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    targeting
    0.74
    텅
    0.71
    Strateg
    0.69
     targeting
    0.66
     વોર્
    0.64
     sistema
    0.64
     기능을
    0.64
     Targeting
    0.62
    Target
    0.62
    Alarm
    0.61
    POSITIVE LOGITS
     experiences
    2.84
     Experiences
    2.58
    experiences
    2.52
     experiencias
    2.51
     experience
    2.51
     experiências
    2.49
    Experiences
    2.41
     experiência
    2.33
     Experience
    2.30
     esperienze
    2.28
    Act Density 0.138%

    No Known Activations