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

    Neuronpedia

    INDEX
    Explanations

    underline

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uuid
    -0.07
     Success
    -0.07
    goo
    -0.07
    -alert
    -0.07
    OOK
    -0.06
    oy
    -0.06
     경우
    -0.06
    ’av
    -0.06
    OMIC
    -0.06
     número
    -0.06
    POSITIVE LOGITS
    xford
    0.07
     대학
    0.06
     перег
    0.06
     суб
    0.06
     Switzerland
    0.06
    dogs
    0.06
    chemistry
    0.06
    Corn
    0.06
    trecht
    0.06
    ISTER
    0.06
    Act Density 0.010%

    No Known Activations