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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    後の
    -0.06
     �
    -0.06
     llegar
    -0.06
     жовтня
    -0.06
     Περι
    -0.06
    uco
    -0.06
    stras
    -0.06
    expired
    -0.06
    、な
    -0.06
    áři
    -0.06
    POSITIVE LOGITS
     resurrection
    0.06
     DataSet
    0.06
     Mormon
    0.06
     infile
    0.06
    shaled
    0.06
    거
    0.06
    walking
    0.06
    alignment
    0.06
    gest
    0.06
    dogs
    0.06
    Act Density 0.000%

    No Known Activations