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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raj
    -0.07
     Crunch
    -0.07
     drawer
    -0.06
    .exp
    -0.06
     rune
    -0.06
     Amendments
    -0.06
     Dynamics
    -0.06
    汉堡
    -0.06
    missive
    -0.06
     Roo
    -0.06
    POSITIVE LOGITS
    얻
    0.07
     embroid
    0.07
    웸
    0.07
    akhir
    0.06
    =[]
↵
    0.06
    =nil
    0.06
    	initial
    0.06
    !");
↵
    0.06
    []↵
    0.06
    Expose
    0.06
    Act Density 0.005%

    No Known Activations