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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slit
    -0.08
     От
    -0.08
     cups
    -0.07
    "]).
    -0.07
    emes
    -0.07
    /pages
    -0.07
     cup
    -0.07
     yelling
    -0.07
    缨
    -0.07
     humming
    -0.06
    POSITIVE LOGITS
    throp
    0.07
    StartPosition
    0.07
    аци
    0.07
     располож
    0.07
    RW
    0.07
    ystatechange
    0.07
    ]--;↵
    0.07
    �
    0.07
    \"";↵
    0.07
    �
    0.06
    Act Density 0.005%

    No Known Activations