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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Venom
    -0.07
     Tac
    -0.06
    .mul
    -0.06
     desc
    -0.06
     stub
    -0.06
     cole
    -0.06
    itional
    -0.06
    筒
    -0.06
     button
    -0.06
    ges
    -0.06
    POSITIVE LOGITS
    обходим
    0.07
     kf
    0.06
     Ví
    0.06
    (KP
    0.06
     CAMERA
    0.06
    illing
    0.06
     coronavirus
    0.06
     pledge
    0.06
     coloring
    0.06
    :"
    0.06
    Act Density 0.007%

    No Known Activations