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

    Neuronpedia

    INDEX
    Explanations

    url

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     は
    -0.07
     steadily
    -0.07
     CF
    -0.07
     开
    -0.07
    IntoConstraints
    -0.06
     Senator
    -0.06
    원을
    -0.06
     Som
    -0.06
     thunk
    -0.06
    "F
    -0.06
    POSITIVE LOGITS
     url
    0.07
    irse
    0.07
     squid
    0.07
    zoek
    0.07
    }
↵
↵
    0.06
    itted
    0.06
    /ml
    0.06
    (ix
    0.06
    lvl
    0.06
    ِل
    0.06
    Act Density 0.001%

    No Known Activations