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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кут
    -0.07
    VEN
    -0.07
     механіз
    -0.07
     Mixer
    -0.07
    шим
    -0.07
     presses
    -0.07
     model
    -0.07
     models
    -0.07
     RAID
    -0.06
     dummy
    -0.06
    POSITIVE LOGITS
     ontvangst
    0.06
     acknowledgement
    0.06
     solic
    0.06
     så
    0.06
    .Low
    0.06
    醴
    0.06
    olf
    0.05
     ##↵
    0.05
    .Edit
    0.05
    .shop
    0.05
    Act Density 0.020%

    No Known Activations