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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NO
    -0.08
     Iraq
    -0.07
     put
    -0.07
    .Save
    -0.07
     equip
    -0.07
     Yi
    -0.07
     Successful
    -0.07
    خص
    -0.07
    -copy
    -0.07
    emies
    -0.07
    POSITIVE LOGITS
     between
    0.07
     mitochond
    0.06
    かって
    0.06
    .pb
    0.06
     �
    0.06
    rightarrow
    0.06
     debated
    0.06
    lassen
    0.06
    _MODULES
    0.05
    allah
    0.05
    Act Density 0.010%

    No Known Activations