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

    Neuronpedia

    INDEX
    Explanations

    virtual machine configuration instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Paris
    -0.08
    ๒
    -0.08
     ית
    -0.08
    后来
    -0.08
     Dateien
    -0.08
    netje
    -0.08
     básico
    -0.08
    'idée
    -0.08
     Nein
    -0.08
    רע
    -0.08
    POSITIVE LOGITS
     responsible
    0.07
     frameworks
    0.07
    respons
    0.07
     earning
    0.07
     alan
    0.07
     refers
    0.07
     Responsible
    0.07
     esteemed
    0.07
    .heading
    0.07
     earned
    0.07
    Act Density 0.006%

    No Known Activations