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

    Neuronpedia

    INDEX
    Explanations

    boolean values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VH
    -0.07
     invis
    -0.07
     Mistress
    -0.07
    _VM
    -0.07
     Ге
    -0.06
     Lid
    -0.06
     GIS
    -0.06
    Dup
    -0.06
     clan
    -0.06
    Group
    -0.06
    POSITIVE LOGITS
    ↵
    0.07
      ↵
    0.06
     захворю
    0.06
    χώ
    0.06
     fostering
    0.06
    Sketch
    0.06
     Petite
    0.06
    _boost
    0.06
    imals
    0.06
    tright
    0.06
    Act Density 0.012%

    No Known Activations