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

    Neuronpedia

    INDEX
    Explanations

    `(` followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CA
    0.48
    관
    0.48
    BC
    0.47
    Burn
    0.46
    ');
    0.46
    Current
    0.45
    その後
    0.45
    Ç
    0.45
    мок
    0.44
    ான
    0.44
    POSITIVE LOGITS
     brine
    0.57
     relish
    0.55
     mulch
    0.53
    risome
    0.51
     rut
    0.49
     raspberry
    0.49
     rupee
    0.49
     outsource
    0.49
     rhino
    0.48
     vaccines
    0.48
    Act Density 0.000%

    No Known Activations