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

    Neuronpedia

    INDEX
    Explanations

    Code/Math Equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     대한
    -0.07
     deter
    -0.07
     Protestant
    -0.06
     Lean
    -0.06
    groupon
    -0.06
    submitted
    -0.06
     Ethi
    -0.06
    Bal
    -0.06
    âh
    -0.06
    USES
    -0.06
    POSITIVE LOGITS
     transporting
    0.07
    Transport
    0.06
    ,callback
    0.06
    _<
    0.06
     localized
    0.06
    _ag
    0.06
     �
    0.06
    ;r
    0.06
    _RESP
    0.06
    _cast
    0.06
    Act Density 0.022%

    No Known Activations