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

    Neuronpedia

    INDEX
    Explanations

    code or documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ci
    -0.07
    όρ
    -0.06
    591
    -0.06
     loosely
    -0.06
    а�
    -0.06
    .k
    -0.06
    ída
    -0.06
    inee
    -0.06
    .mob
    -0.05
    Broadcast
    -0.05
    POSITIVE LOGITS
     tir
    0.07
     buffers
    0.07
    階
    0.07
    위를
    0.07
    吸
    0.06
    (message
    0.06
     Allan
    0.06
     PRODUCT
    0.06
    (true
    0.06
     Welt
    0.06
    Act Density 0.000%

    No Known Activations