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

    Neuronpedia

    INDEX
    Explanations

    to + modifier/verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бло
    0.88
    러
    0.73
     Missing
    0.70
     Batch
    0.69
    चुरल
    0.69
     batch
    0.69
     tempted
    0.68
    Batch
    0.67
    CONT
    0.67
    abang
    0.66
    POSITIVE LOGITS
    ppling
    1.06
     coincide
    1.06
     commemorate
    0.96
    pples
    0.95
     avoid
    0.94
     promote
    0.93
     penetrate
    0.92
     encompass
    0.92
    ilets
    0.92
     fruition
    0.91
    Act Density 0.939%

    No Known Activations