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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twitter
    -0.07
     lee
    -0.07
     LS
    -0.06
     amidst
    -0.06
    ,list
    -0.06
     bushes
    -0.06
     paradigm
    -0.06
     thru
    -0.06
    &S
    -0.06
    _storage
    -0.06
    POSITIVE LOGITS
    .'<
    0.08
    "]
↵
    0.07
    HasColumnName
    0.07
     substantially
    0.07
     JavaScript
    0.07
     afterward
    0.07
    ']
↵
    0.07
     }
↵
↵
    0.06
     canceled
    0.06
     marshal
    0.06
    Act Density 0.285%

    No Known Activations