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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艘
    -0.07
    (args
    -0.07
    մ
    -0.06
    .shape
    -0.06
    (ch
    -0.06
     south
    -0.06
    rig
    -0.06
    .awt
    -0.06
    through
    -0.06
     feat
    -0.06
    POSITIVE LOGITS
    收到
    0.07
     kut
    0.07
    꺅
    0.07
    shows
    0.07
    .Entry
    0.06
    zik
    0.06
    酅
    0.06
    圊
    0.06
    .presentation
    0.06
    娛
    0.06
    Act Density 0.015%

    No Known Activations