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

    Neuronpedia

    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Area
    -0.07
    gf
    -0.07
    -made
    -0.07
     Pa
    -0.07
    marca
    -0.07
     forwards
    -0.07
     daycare
    -0.07
    ibri
    -0.07
    Derived
    -0.06
    다고
    -0.06
    POSITIVE LOGITS
     cruising
    0.07
    ]?
    0.06
    lum
    0.06
     LESS
    0.06
     rootView
    0.06
     experimented
    0.06
    .InnerException
    0.06
    opens
    0.05
    Originally
    0.05
     anticipation
    0.05
    Act Density 0.001%

    No Known Activations