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

    Neuronpedia

    INDEX
    Explanations

    Reasons and justifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .progress
    -0.07
    .`);↵
    -0.06
     体
    -0.06
    ssc
    -0.06
     Tucker
    -0.06
    MSC
    -0.06
    َأ
    -0.06
    artz
    -0.06
    .ID
    -0.06
    KL
    -0.06
    POSITIVE LOGITS
     Late
    0.08
    .assign
    0.07
    ylon
    0.07
     riv
    0.06
    _directory
    0.06
     Recorder
    0.06
     Fres
    0.06
     exploration
    0.06
    _trim
    0.06
    inate
    0.06
    Act Density 0.006%

    No Known Activations