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

    Neuronpedia

    INDEX
    Explanations

    Gen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estival
    -0.07
     prive
    -0.07
    938
    -0.07
     part
    -0.06
    .drop
    -0.06
    dro
    -0.06
    arsers
    -0.06
     الدولة
    -0.06
    ure
    -0.06
    TRS
    -0.06
    POSITIVE LOGITS
     Germany
    0.09
    ermann
    0.08
    ßen
    0.08
    üsseldorf
    0.08
    .de
    0.07
    utschein
    0.07
     Munich
    0.07
    lsruhe
    0.07
    mbH
    0.07
    Germany
    0.07
    Act Density 0.889%

    No Known Activations