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

    Neuronpedia

    INDEX
    Explanations

    object detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruined
    -0.06
     причина
    -0.06
    thus
    -0.06
     Denmark
    -0.06
     ledger
    -0.06
     hinge
    -0.05
    -mouth
    -0.05
    antu
    -0.05
    acha
    -0.05
     tồn
    -0.05
    POSITIVE LOGITS
    81
    0.07
    .property
    0.07
     Erotische
    0.07
     RECE
    0.06
    home
    0.06
    unately
    0.06
     alarak
    0.06
     tecn
    0.06
    255
    0.06
     setup
    0.06
    Act Density 0.005%

    No Known Activations