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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jal
    -0.07
    ("-");↵
    -0.06
     chocolates
    -0.06
     mất
    -0.06
     Railway
    -0.06
    alice
    -0.06
    .lift
    -0.06
     melodies
    -0.06
    hydrate
    -0.06
    ชาต
    -0.06
    POSITIVE LOGITS
    /port
    0.08
    }}>↵
    0.07
    /new
    0.07
     principio
    0.07
     nghề
    0.07
     stringWithFormat
    0.06
     vrch
    0.06
     بص
    0.06
    ruptcy
    0.06
     اداره
    0.06
    Act Density 0.014%

    No Known Activations