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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -needed
    -0.07
     election
    -0.07
     long
    -0.06
     planet
    -0.06
     heiß
    -0.06
     opposite
    -0.06
     nuclear
    -0.06
    Fast
    -0.06
     icy
    -0.06
     dialogue
    -0.06
    POSITIVE LOGITS
    FPS
    0.06
    艇
    0.06
     {
↵
↵
↵
    0.06
    cribes
    0.06
    ,:)
    0.06
     PICK
    0.06
    })",
    0.06
    .detach
    0.06
    ++)
↵
    0.06
    _AVAILABLE
    0.06
    Act Density 0.313%

    No Known Activations