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

    Neuronpedia

    INDEX
    Explanations

    details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _JOIN
    -0.07
    ("(
    -0.06
    (mask
    -0.06
    MU
    -0.06
    ynamo
    -0.06
    	sql
    -0.06
    	op
    -0.06
    (z
    -0.06
     (_
    -0.06
     Mom
    -0.06
    POSITIVE LOGITS
     Details
    0.10
     details
    0.08
     Irene
    0.08
     DETAILS
    0.07
    ensation
    0.07
     cảnh
    0.07
    alex
    0.07
     particulars
    0.07
    _pemb
    0.07
    Detail
    0.06
    Act Density 0.007%

    No Known Activations