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
     signal
    -0.06
     Shall
    -0.06
     içine
    -0.06
     evenings
    -0.06
     hton
    -0.06
    .Xtra
    -0.06
     forecast
    -0.06
    Camera
    -0.06
     každé
    -0.06
    CanBe
    -0.06
    POSITIVE LOGITS
    (/\
    0.06
    configs
    0.06
    .stats
    0.06
    (px
    0.06
    UseProgram
    0.06
     Not
    0.06
    换
    0.06
     turnout
    0.06
     try
    0.06
    _xx
    0.06
    Act Density 0.005%

    No Known Activations