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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ircle
    -0.07
     sentencing
    -0.07
     tbsp
    -0.07
     Shoulder
    -0.07
    -Year
    -0.06
     Seventh
    -0.06
     thermostat
    -0.06
    莺
    -0.06
    experiment
    -0.06
    ∇
    -0.06
    POSITIVE LOGITS
    ไท
    0.07
    ân
    0.07
    暗暗
    0.07
    (float
    0.07
     chai
    0.07
    ﻀ
    0.07
     Danish
    0.07
    干燥
    0.07
     Box
    0.07
    صيانة
    0.06
    Act Density 0.021%

    No Known Activations