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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pone
    -0.07
    necessary
    -0.07
    dlg
    -0.07
     komp
    -0.07
    (change
    -0.07
     Faces
    -0.07
     explanations
    -0.07
     updated
    -0.06
     this
    -0.06
    Vin
    -0.06
    POSITIVE LOGITS
    CG
    0.06
    rač
    0.06
     Powered
    0.06
    帽
    0.06
    _books
    0.06
     aş
    0.06
    كة
    0.05
     �
    0.05
    \Active
    0.05
     OpenFileDialog
    0.05
    Act Density 0.021%

    No Known Activations