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

    Neuronpedia

    INDEX
    Explanations

    Describing processes/examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //----------------
    -0.06
     blok
    -0.06
     vstup
    -0.06
    .tiles
    -0.06
    uffle
    -0.06
     hal
    -0.06
    	ptr
    -0.06
     Pence
    -0.06
    	SET
    -0.06
     Verde
    -0.06
    POSITIVE LOGITS
    (guild
    0.06
    ระหว
    0.06
    (labels
    0.06
     заболеваний
    0.06
    िछल
    0.05
    orea
    0.05
     briefed
    0.05
     fileId
    0.05
    орд
    0.05
    -host
    0.05
    Act Density 0.229%

    No Known Activations