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

    Neuronpedia

    INDEX
    Explanations

    checkpoint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mapped
    -0.07
    Metadata
    -0.07
     Problems
    -0.07
    ollapsed
    -0.06
     chickens
    -0.06
     McCartney
    -0.06
     horm
    -0.06
     Mö
    -0.06
     چند
    -0.06
     peach
    -0.06
    POSITIVE LOGITS
    (store
    0.06
    (pf
    0.06
     abst
    0.06
     bieten
    0.06
    。その
    0.06
     Ventures
    0.06
    hes
    0.06
    EEP
    0.06
     vự
    0.06
     desks
    0.06
    Act Density 0.012%

    No Known Activations