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

    Neuronpedia

    INDEX
    Explanations

    sense of belonging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     new
    0.44
     Tomato
    0.43
     Beads
    0.43
    olly
    0.41
                   
    0.41
    usse
    0.41
     নতুন
    0.40
     Milk
    0.40
    iala
    0.40
     Vector
    0.39
    POSITIVE LOGITS
     outweighs
    0.46
    seekers
    0.43
    стрее
    0.43
    ීර
    0.43
     هە
    0.41
     endangering
    0.41
     అక్కడ
    0.40
     profundidad
    0.40
    Rena
    0.40
     ওখানে
    0.40
    Act Density 0.000%

    No Known Activations