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

    Neuronpedia

    INDEX
    Explanations

    yp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脓
    -0.07
    zens
    -0.07
     conject
    -0.07
     blobs
    -0.06
    群岛
    -0.06
     bl
    -0.06
    гу
    -0.06
     coração
    -0.06
     willingly
    -0.06
     delve
    -0.06
    POSITIVE LOGITS
    ណ
    0.07
    ิต
    0.07
    głow
    0.07
    (camera
    0.07
    	Local
    0.07
     smoothing
    0.06
    0.06
    맀
    0.06
    פצ
    0.06
    原材料
    0.06
    Act Density 0.001%

    No Known Activations