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

    Neuronpedia

    INDEX
    Explanations

    offices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leaves
    -0.08
     Provides
    -0.07
     Proceed
    -0.07
    感冒
    -0.07
     Laure
    -0.07
     Cue
    -0.07
    viewer
    -0.07
    无助
    -0.07
    	cin
    -0.07
     To
    -0.06
    POSITIVE LOGITS
    arming
    0.08
     availability
    0.07
    水利
    0.07
    _logits
    0.07
     network
    0.07
    妤
    0.07
    .parameters
    0.07
    \":\"
    0.07
     nosso
    0.07
    atomy
    0.06
    Act Density 0.036%

    No Known Activations