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

    Neuronpedia

    INDEX
    Explanations

    Medical advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unfolds
    -0.06
     villains
    -0.06
    publish
    -0.06
    sleep
    -0.06
    FFT
    -0.06
     fan
    -0.06
     refurbished
    -0.06
     �
    -0.06
    reten
    -0.06
     wagon
    -0.06
    POSITIVE LOGITS
     Scandin
    0.07
    uto
    0.07
    achie
    0.07
     đối
    0.07
     Rotterdam
    0.07
     Serialize
    0.06
    бав
    0.06
     informace
    0.06
    /problem
    0.06
     قوان
    0.06
    Act Density 0.045%

    No Known Activations