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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     people
    -0.07
     oxygen
    -0.07
     Oxygen
    -0.07
     decreases
    -0.06
     Lewis
    -0.06
     relative
    -0.06
    391
    -0.06
     decreased
    -0.06
    Psi
    -0.06
     Rubin
    -0.06
    POSITIVE LOGITS
    Stage
    0.09
     stage
    0.09
    stage
    0.08
     اج
    0.08
     Stage
    0.08
     松
    0.08
     Çağ
    0.07
    	tag
    0.07
     �
    0.07
     cg
    0.07
    Act Density 0.017%

    No Known Activations