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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _delta
    -0.06
     uncovered
    -0.06
     dearly
    -0.06
    	JSONObject
    -0.06
     فران
    -0.06
    Sampling
    -0.06
     miraculous
    -0.06
    (items
    -0.06
     animated
    -0.06
     Fog
    -0.06
    POSITIVE LOGITS
     BH
    0.08
     kế
    0.06
    (),'
    0.06
    Emb
    0.06
    =C
    0.06
     delt
    0.06
     méně
    0.06
    /host
    0.06
     зв
    0.06
    ovny
    0.06
    Act Density 0.014%

    No Known Activations