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

    Neuronpedia

    INDEX
    Explanations

    appendix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .esp
    -0.07
     urb
    -0.07
    N
    -0.07
    orne
    -0.07
     Widow
    -0.07
     görüntü
    -0.07
     stride
    -0.07
    }");↵↵
    -0.07
     forControlEvents
    -0.07
     jednocze
    -0.06
    POSITIVE LOGITS
    already
    0.08
    particle
    0.07
    _COLL
    0.07
    .ARR
    0.07
    .jpa
    0.07
    .I
    0.07
    (policy
    0.07
     Raider
    0.06
    	G
    0.06
    apyrus
    0.06
    Act Density 0.001%

    No Known Activations