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

    Neuronpedia

    INDEX
    Explanations

    repetitive text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eff
    0.41
    aines
    0.39
    Vista
    0.38
     کرا
    0.38
    elastic
    0.38
     ef
    0.37
    次
    0.37
    忻
    0.37
    Am
    0.36
    ↩
    0.36
    POSITIVE LOGITS
     Neighbors
    0.42
     Tower
    0.41
     Cougars
    0.40
     വൈദ്യുതി
    0.40
     unicorns
    0.40
     Pyrénées
    0.39
     അര
    0.39
     daarbij
    0.39
     يكون
    0.38
     unicorn
    0.38
    Act Density 0.000%

    No Known Activations