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

    Neuronpedia

    INDEX
    Explanations

    cases, still not, whales undertake, highly scalable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rhod
    0.46
    ogeneous
    0.45
     every
    0.44
     deepest
    0.44
    安い
    0.44
     Erik
    0.43
     that
    0.42
     anisotropy
    0.42
     upcoming
    0.42
     exploded
    0.42
    POSITIVE LOGITS
     quản
    0.47
     sustancias
    0.45
    Multiple
    0.44
     vulve
    0.44
    umba
    0.43
     múlt
    0.42
    ván
    0.42
     buscan
    0.42
     ngừng
    0.42
     бути
    0.42
    Act Density 0.002%

    No Known Activations