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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     인증
    -0.07
     spiral
    -0.07
     drinks
    -0.06
    野
    -0.06
    Password
    -0.06
    	valid
    -0.06
     manager
    -0.06
    Serv
    -0.06
    .Params
    -0.06
    Initial
    -0.06
    POSITIVE LOGITS
    (..
    0.07
    resden
    0.07
     ICT
    0.07
    μφ
    0.06
    .contrib
    0.06
    <nav
    0.06
    τή
    0.06
     Knoxville
    0.06
    Bezier
    0.06
    iseconds
    0.06
    Act Density 0.007%

    No Known Activations