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

    Neuronpedia

    INDEX
    Explanations

    characterizing complex situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yet
    0.83
    ?
    0.75
    source
    0.74
    .
    0.72
    Source
    0.71
     or
    0.70
    Having
    0.69
    accia
    0.68
     Source
    0.68
     источ
    0.68
    POSITIVE LOGITS
     humbling
    1.07
     momentous
    1.06
     stressful
    1.06
     windy
    1.06
     heartbreaking
    1.04
     heartwarming
    1.04
     shame
    1.00
     tricky
    0.99
     pity
    0.97
     bumpy
    0.97
    Act Density 0.139%

    No Known Activations