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

    Neuronpedia

    INDEX
    Explanations

    encoder/decoder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lære
    -0.08
     صحة
    -0.08
    ummi
    -0.08
     בסיס
    -0.08
     discovering
    -0.08
     פעילות
    -0.08
     Seminary
    -0.08
    cdecl
    -0.08
    ోగ
    -0.08
    ître
    -0.08
    POSITIVE LOGITS
     injection
    0.09
     inserted
    0.09
    指导
    0.09
     guiding
    0.08
     guider
    0.08
     heter
    0.08
     conditioning
    0.08
     posterior
    0.08
     controls
    0.07
     injected
    0.07
    Act Density 0.003%

    No Known Activations