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

    Neuronpedia

    INDEX
    Explanations

    code structure symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anish
    0.79
     }
    0.77
     deterministic
    0.75
     reinforce
    0.72
     ha
    0.71
     Angriff
    0.71
     onion
    0.69
     Side
    0.68
     Without
    0.68
     ghost
    0.68
    POSITIVE LOGITS
    (
    0.74
    └
    0.72
    {
    0.71
    └──
    0.69
    ([
    0.69
    &&
    0.66
    ((
    0.66
    accordo
    0.64
    (((
    0.63
    ברת
    0.63
    Act Density 0.020%

    No Known Activations