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

    Neuronpedia

    INDEX
    Explanations

    rallying cry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Einstein
    0.43
    requ
    0.42
     Terraform
    0.38
    Einstein
    0.38
     Ba
    0.38
    essential
    0.37
    tact
    0.37
     Aguilar
    0.37
    Collision
    0.37
     Ruby
    0.36
    POSITIVE LOGITS
     rallying
    0.95
     rally
    0.88
     rallied
    0.85
     Rally
    0.77
     rallies
    0.76
     रैली
    0.75
    rally
    0.69
     mobilizing
    0.59
     attorno
    0.54
     rall
    0.49
    Act Density 0.002%

    No Known Activations