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

    Neuronpedia

    INDEX
    Explanations

    Go web server code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    1.31
    OR
    1.24
    Z
    1.14
    G
    1.13
    U
    1.13
    IS
    1.12
    IN
    1.11
    AL
    1.07
    OM
    1.06
    OP
    1.06
    POSITIVE LOGITS
     doenças
    1.53
     adulthood
    1.35
     wildfires
    1.32
     consequências
    1.32
     adolescents
    1.31
     crianças
    1.31
     século
    1.27
     adoles
    1.27
     tokamaks
    1.26
     hemicontinuous
    1.26
    Act Density 0.000%

    No Known Activations