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

    Neuronpedia

    INDEX
    Explanations

    Technical issues and fixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flip
    -0.08
     smashed
    -0.08
     destination
    -0.07
    کش
    -0.07
    Focus
    -0.07
    амп
    -0.07
     button
    -0.07
     preservation
    -0.07
     glass
    -0.07
     Interest
    -0.06
    POSITIVE LOGITS
     농
    0.06
    ■■
    0.06
     pthread
    0.06
    .Annotation
    0.06
    .setModel
    0.06
     (?)
    0.06
     SCIP
    0.06
    .NewGuid
    0.06
    ní
    0.06
    /><
    0.06
    Act Density 0.150%

    No Known Activations