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

    Neuronpedia

    INDEX
    Explanations

    historical figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scriptures
    -0.06
     cabinet
    -0.06
     Bangladesh
    -0.06
    ıkl
    -0.06
    pes
    -0.06
    Nullable
    -0.06
     frü
    -0.06
    -package
    -0.06
    ら
    -0.06
    키
    -0.06
    POSITIVE LOGITS
     titten
    0.06
    �
    0.06
     راه
    0.06
    .FR
    0.06
    .alignment
    0.06
     targ
    0.06
    .Substring
    0.06
    .wall
    0.06
    [iVar
    0.06
     Ronnie
    0.06
    Act Density 0.067%

    No Known Activations