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

    Neuronpedia

    INDEX
    Explanations

    Solving equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WRAPPER
    -0.07
     sev
    -0.06
     selv
    -0.06
    (Direction
    -0.06
    uvwxyz
    -0.06
     mitigation
    -0.06
    Duplicate
    -0.06
    sequent
    -0.06
    (_.
    -0.06
    .Filter
    -0.06
    POSITIVE LOGITS
    出来
    0.08
     orientation
    0.07
     �
    0.07
    arası
    0.07
     coorden
    0.07
     감
    0.06
     hooked
    0.06
     improvis
    0.06
    �
    0.06
    よう
    0.06
    Act Density 0.020%

    No Known Activations