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

    Neuronpedia

    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    commend
    -0.07
    ावर
    -0.07
    ẫn
    -0.06
     etraf
    -0.06
     정부
    -0.06
    simulation
    -0.06
    イス
    -0.06
     rays
    -0.06
     이를
    -0.06
    .story
    -0.06
    POSITIVE LOGITS
     nhà
    0.06
     huy
    0.06
     Cannot
    0.06
    .Roles
    0.06
     colspan
    0.06
    .slice
    0.06
     indice
    0.06
     colourful
    0.06
     Needle
    0.06
     EVENT
    0.06
    Act Density 0.003%

    No Known Activations