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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sweet
    -0.07
    ruits
    -0.07
     Somalia
    -0.07
    _TLS
    -0.06
     inheritance
    -0.06
    .returnValue
    -0.06
    	that
    -0.06
    foot
    -0.06
    来た
    -0.06
     recruits
    -0.06
    POSITIVE LOGITS
    px
    0.08
    代理
    0.07
     Λ
    0.06
     quarterly
    0.06
     olmasına
    0.06
     ');↵↵
    0.06
     endanger
    0.06
    廠
    0.06
     SWITCH
    0.06
    crafted
    0.06
    Act Density 0.001%

    No Known Activations