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

    Neuronpedia

    INDEX
    Explanations

    Bats

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لوبی
    0.63
     rushes
    0.61
     التمث
    0.57
     竹
    0.53
     exit
    0.52
     gall
    0.50
     thereto
    0.50
    栏
    0.50
    煞
    0.50
     locks
    0.50
    POSITIVE LOGITS
     bats
    0.57
     Bats
    0.57
    BATCH
    0.55
    нити
    0.53
     Good
    0.52
    Bats
    0.51
    bat
    0.51
    icester
    0.50
    dürü
    0.50
     collisions
    0.50
    Act Density 0.000%

    No Known Activations