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

    Neuronpedia

    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عشر
    -0.07
     wird
    -0.07
    ьми
    -0.06
     Но
    -0.06
     основ
    -0.06
    人
    -0.06
     zombie
    -0.06
    ереч
    -0.06
     registrazione
    -0.06
    _nombre
    -0.06
    POSITIVE LOGITS
     UNSIGNED
    0.07
     glasses
    0.06
    )$/
    0.06
    .Controls
    0.06
     ±
    0.06
    pm
    0.06
    :'',
    0.06
     domin
    0.06
     strategically
    0.06
    	board
    0.06
    Act Density 0.001%

    No Known Activations