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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Syria
    -0.07
     seen
    -0.07
     magistrate
    -0.07
     Sofia
    -0.07
    Imm
    -0.07
     POV
    -0.07
    kan
    -0.06
    ㅠㅠ
    -0.06
     Ethiopia
    -0.06
    flix
    -0.06
    POSITIVE LOGITS
    .setter
    0.07
    named
    0.07
     використання
    0.07
     BufferedWriter
    0.07
    amel
    0.06
     паци
    0.06
    282
    0.06
     getMenuInflater
    0.06
     correctamente
    0.06
     WITH
    0.06
    Act Density 0.001%

    No Known Activations