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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comer
    -0.06
     bikes
    -0.06
     hunted
    -0.06
    +/
    -0.06
    _micro
    -0.06
     petals
    -0.06
    .Gravity
    -0.06
    916
    -0.06
    languages
    -0.06
    
    -0.06
    POSITIVE LOGITS
     olduğuna
    0.08
    efully
    0.07
    (iterator
    0.06
     yi
    0.06
     olmasına
    0.06
    「え
    0.06
     Skin
    0.06
    ші
    0.06
     tendency
    0.06
     combating
    0.06
    Act Density 0.000%

    No Known Activations