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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mont
    0.47
    Buff
    0.44
     الاش
    0.39
    Aff
    0.39
    Inc
    0.38
    Acceleration
    0.38
    Neg
    0.37
    Sou
    0.37
    ATT
    0.37
     Surge
    0.36
    POSITIVE LOGITS
     Teflon
    0.48
     слад
    0.44
    ystems
    0.44
     sweet
    0.43
     আলোচনায়
    0.43
     répand
    0.41
    螂
    0.41
     propellant
    0.40
     nadi
    0.40
     audience
    0.39
    Act Density 0.001%

    No Known Activations