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

    Neuronpedia

    INDEX
    Explanations

    academic research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Castle
    -0.08
     knight
    -0.06
     Castle
    -0.06
     begun
    -0.06
    fv
    -0.06
    Aside
    -0.06
    Tim
    -0.06
    *=*=
    -0.06
    acho
    -0.06
     Vil
    -0.06
    POSITIVE LOGITS
     bilir
    0.06
     τε
    0.06
     NgModule
    0.06
     ourselves
    0.06
    LOAT
    0.06
    itesse
    0.06
    (module
    0.06
    لاث
    0.06
     vzdál
    0.06
    )}
    0.06
    Act Density 0.035%

    No Known Activations