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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vět
    -0.07
     заключ
    -0.07
     rollout
    -0.06
    .linear
    -0.06
     دختر
    -0.06
    嗯
    -0.06
     CommandType
    -0.06
    pecified
    -0.06
    angers
    -0.06
    Gradient
    -0.06
    POSITIVE LOGITS
     spoke
    0.06
     taj
    0.06
     Cornel
    0.06
     LIABILITY
    0.06
    ωμα
    0.06
    ('%
    0.06
     pretend
    0.06
    Den
    0.06
    /start
    0.06
     canon
    0.06
    Act Density 0.152%

    No Known Activations