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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ViewHolder
    -0.07
     anlayış
    -0.07
     sett
    -0.07
    Redux
    -0.06
     Wis
    -0.06
    /save
    -0.06
    คน
    -0.06
    resident
    -0.06
    -n
    -0.06
    Mob
    -0.06
    POSITIVE LOGITS
     papel
    0.07
    _xpath
    0.07
    ◆
    0.06
     Illustr
    0.06
     gord
    0.06
     Αρ
    0.06
     [...]
    0.06
     απο
    0.06
     azal
    0.06
     serialize
    0.06
    Act Density 0.020%

    No Known Activations