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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wreckage
    -0.07
    �
    -0.07
     네
    -0.06
    .ticket
    -0.06
    867
    -0.06
    \Configuration
    -0.06
     вб
    -0.06
    .RightToLeft
    -0.05
    元
    -0.05
    努
    -0.05
    POSITIVE LOGITS
    _diag
    0.07
    (controller
    0.07
     afternoon
    0.07
    (interval
    0.07
     disturb
    0.06
     accelerated
    0.06
    iado
    0.06
    ighborhood
    0.06
     Hard
    0.06
     pardon
    0.06
    Act Density 0.001%

    No Known Activations