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

    Neuronpedia

    INDEX
    Explanations

    say "crossing movements"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Join
    -0.07
    strate
    -0.07
    _TURN
    -0.07
    Pix
    -0.07
    teen
    -0.07
    ality
    -0.07
    ASH
    -0.07
     strain
    -0.07
    Stars
    -0.07
     timestep
    -0.06
    POSITIVE LOGITS
     기능
    0.06
     كور
    0.06
     إ
    0.06
    �
    0.06
    _DEFINITION
    0.06
     số
    0.06
     equivalent
    0.05
    .Expression
    0.05
     trục
    0.05
    -Tr
    0.05
    Act Density 0.025%

    No Known Activations