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

    Neuronpedia

    INDEX
    Explanations

    -ectomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     channels
    -0.07
     throat
    -0.07
     lai
    -0.07
    laş
    -0.06
     traff
    -0.06
     Specifies
    -0.06
    ToOne
    -0.06
    �
    -0.06
    し
    -0.06
     overturned
    -0.06
    POSITIVE LOGITS
    ectomy
    0.09
     PhD
    0.07
    EP
    0.06
    нима
    0.06
     Totally
    0.06
     KeyEvent
    0.06
     Landing
    0.06
    award
    0.06
    atom
    0.06
    Amy
    0.06
    Act Density 0.014%

    No Known Activations