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

    Neuronpedia

    INDEX
    Explanations

    arbitration and sabotage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slumber
    0.47
     Lend
    0.43
     abode
    0.43
     neat
    0.42
     caviar
    0.42
     slain
    0.42
     puddle
    0.42
     cube
    0.41
     lend
    0.40
     cobra
    0.40
    POSITIVE LOGITS
    uria
    0.50
    isak
    0.47
    Planning
    0.46
    Interview
    0.46
    zani
    0.46
     Biotechnol
    0.46
    ivé
    0.45
    ona
    0.44
    on
    0.44
    éria
    0.44
    Act Density 0.028%

    No Known Activations