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

    Neuronpedia

    INDEX
    Explanations

    Ryan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    theless
    -0.07
     Hole
    -0.07
    .coll
    -0.07
    控制
    -0.06
     стол
    -0.06
    dol
    -0.06
    ortic
    -0.06
     respects
    -0.06
     Idle
    -0.06
    	reg
    -0.06
    POSITIVE LOGITS
     Ryan
    0.18
    Ryan
    0.17
     Sean
    0.10
     Bryan
    0.09
    ryan
    0.09
    Sean
    0.08
     Megan
    0.08
    -Ray
    0.08
     Liam
    0.08
     sean
    0.07
    Act Density 0.002%

    No Known Activations