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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     compr
    -0.07
    remember
    -0.07
    ieve
    -0.06
    traits
    -0.06
     hamburger
    -0.06
    /type
    -0.06
    rts
    -0.06
    prefer
    -0.06
    ourcem
    -0.06
    POSITIVE LOGITS
     웹사이트
    0.07
    }
↵
↵
    0.07
    resolved
    0.06
     blinked
    0.06
    	Dim
    0.06
     Sergei
    0.06
     tribunal
    0.06
    LOCAL
    0.06
     Fiona
    0.06
     Breitbart
    0.06
    Act Density 0.078%

    No Known Activations