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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sender
    -0.06
     bins
    -0.06
     Pulitzer
    -0.06
     Cars
    -0.06
    /tree
    -0.06
    .answers
    -0.06
    Forward
    -0.06
     identifier
    -0.06
    Bob
    -0.06
    /sql
    -0.06
    POSITIVE LOGITS
     Bethlehem
    0.06
    ownload
    0.06
    (">
    0.06
    ��
    0.06
    �
    0.06
     comforts
    0.06
    oint
    0.06
    .Obj
    0.06
    FileChooser
    0.06
     leftover
    0.06
    Act Density 0.008%

    No Known Activations