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

    Neuronpedia

    INDEX
    Explanations

    escalator motion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prefix
    -0.08
    олч
    -0.08
    Parse
    -0.08
     standout
    -0.08
     terci
    -0.08
    ports
    -0.08
    _prefix
    -0.07
     shipping
    -0.07
    -0.07
    portfolio
    -0.07
    POSITIVE LOGITS
     Accounting
    0.08
     Interviews
    0.08
     collapsing
    0.08
    .linspace
    0.08
     Travers
    0.08
     invariant
    0.08
     Accountant
    0.08
     Changing
    0.08
    ostante
    0.07
     Flücht
    0.07
    Act Density 0.010%
    No Known Activations