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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ming
    -0.07
    rió
    -0.07
     wanna
    -0.07
    قاء
    -0.07
    ům
    -0.07
    男
    -0.07
    �
    -0.06
     trajectories
    -0.06
    ीय
    -0.06
     무엇
    -0.06
    POSITIVE LOGITS
     privileges
    0.07
    _resolver
    0.06
     Jug
    0.06
    yyval
    0.06
    #ifndef
    0.06
    -left
    0.06
     src
    0.06
     Subcommittee
    0.06
    rawl
    0.05
     Drain
    0.05
    Act Density 0.000%

    No Known Activations