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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cla
    -0.07
     acceso
    -0.07
    Marks
    -0.07
    031
    -0.07
    uč
    -0.07
     jedis
    -0.06
     Rajasthan
    -0.06
    Marca
    -0.06
    asti
    -0.06
     executions
    -0.06
    POSITIVE LOGITS
     эту
    0.07
     this
    0.06
    SY
    0.06
    this
    0.06
    tbody
    0.06
     genius
    0.06
    ング
    0.06
     этой
    0.06
     Coconut
    0.06
    escape
    0.06
    Act Density 0.003%

    No Known Activations