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

    Neuronpedia

    INDEX
    Explanations

    words starting with b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antage
    0.91
    oodoo
    0.91
    ouchers
    0.90
    oxel
    0.84
    ulnerable
    0.80
    riters
    0.80
    itesse
    0.79
    icious
    0.79
    restling
    0.78
    ibration
    0.78
    POSITIVE LOGITS
     compete
    0.85
    iphenyl
    0.83
    łąd
    0.81
     lack
    0.78
     Akash
    0.77
    icycles
    0.76
    řez
    0.74
    ouncy
    0.74
     envisage
    0.73
     lacked
    0.73
    Act Density 0.126%

    No Known Activations