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

    Neuronpedia

    INDEX
    Explanations

    destruction/disintegration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     almaktadır
    -0.07
     části
    -0.07
     оконч
    -0.07
    иболее
    -0.07
     वस
    -0.07
     presidency
    -0.07
     Clay
    -0.07
    운데
    -0.06
    オン
    -0.06
    completed
    -0.06
    POSITIVE LOGITS
    /notification
    0.06
     Experiment
    0.06
     Screen
    0.06
    rost
    0.06
     prm
    0.06
     đo
    0.05
     UL
    0.05
    .transport
    0.05
    腹
    0.05
    SCRIPT
    0.05
    Act Density 0.034%

    No Known Activations