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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Railway
    -0.07
     railways
    -0.07
     crushers
    -0.06
     annual
    -0.06
     weak
    -0.06
    :',
    -0.06
    _eye
    -0.06
     unhealthy
    -0.06
     coated
    -0.06
     supply
    -0.06
    POSITIVE LOGITS
    leanor
    0.07
     didFinish
    0.07
    <Member
    0.07
    <Person
    0.07
     Burlington
    0.07
    ประช
    0.07
    .hamcrest
    0.07
     Eleanor
    0.07
     Baldwin
    0.06
    NotAllowed
    0.06
    Act Density 0.004%

    No Known Activations