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

    Neuronpedia

    INDEX
    Explanations

    actions and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Toys
    -0.07
     Ghost
    -0.07
     daughters
    -0.07
     premium
    -0.06
     vertical
    -0.06
     amphib
    -0.06
     Depth
    -0.06
    -series
    -0.06
    Authenticated
    -0.06
     Race
    -0.06
    POSITIVE LOGITS
    ával
    0.07
    vál
    0.06
    яви
    0.06
    [current
    0.06
     dil
    0.06
    그래
    0.06
    StartupScript
    0.06
    	If
    0.06
     mover
    0.06
    ,num
    0.06
    Act Density 0.041%

    No Known Activations