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

    Neuronpedia

    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	response
    -0.07
     عصر
    -0.07
     CCC
    -0.06
    	RETURN
    -0.06
     GPL
    -0.06
     différent
    -0.06
     chang
    -0.06
    nesty
    -0.06
     LDAP
    -0.06
     Something
    -0.06
    POSITIVE LOGITS
    -framework
    0.07
     buena
    0.06
    を作
    0.06
    etics
    0.06
    brain
    0.06
    (network
    0.06
    chi
    0.06
     glu
    0.06
    افی
    0.06
    际
    0.06
    Act Density 0.000%

    No Known Activations