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

    Neuronpedia

    INDEX
    Explanations

    resorting to actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glow
    -0.06
     týd
    -0.06
     homogeneous
    -0.06
    สมเด
    -0.06
    ertainty
    -0.06
    in
    -0.06
    .getParameter
    -0.06
    ือข
    -0.06
    -negative
    -0.05
     Dreams
    -0.05
    POSITIVE LOGITS
     resort
    0.10
     Resort
    0.09
     método
    0.08
     recurs
    0.08
     recursos
    0.08
     recur
    0.08
     recourse
    0.07
    ，最
    0.07
    port
    0.07
     <:
    0.07
    Act Density 0.003%

    No Known Activations