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

    Neuronpedia

    INDEX
    Explanations

    <string

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avorite
    -0.07
    욯
    -0.07
    Cd
    -0.07
     umoż
    -0.07
     reluctance
    -0.07
     zest
    -0.07
    _third
    -0.07
    Choosing
    -0.07
    ución
    -0.07
     Tiên
    -0.07
    POSITIVE LOGITS
     journalist
    0.07
    РО
    0.07
    OM
    0.07
     ();↵
    0.07
    ndon
    0.07
    	F
    0.07
     gramm
    0.07
     spill
    0.07
     GL
    0.07
    .parse
    0.07
    Act Density 0.001%

    No Known Activations