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

    Neuronpedia

    INDEX
    Explanations

    qualifications and drawbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ethoxy
    0.68
    Cl
    0.66
    Phenyl
    0.65
    Automation
    0.65
    Exc
    0.64
    Important
    0.64
    Writing
    0.63
    An
    0.63
    Record
    0.63
    Pl
    0.62
    POSITIVE LOGITS
     melting
    0.60
     (
    0.60
     pitfalls
    0.58
     drawbacks
    0.58
     im
    0.58
     etiquette
    0.58
     limitations
    0.57
     unt
    0.57
     through
    0.57
     swelling
    0.56
    Act Density 0.328%

    No Known Activations