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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .subplots
    -0.07
    Intl
    -0.07
     Аф
    -0.07
     kum
    -0.06
     Πο
    -0.06
     fron
    -0.06
    як
    -0.06
     '\'
    -0.06
    れる
    -0.06
     hak
    -0.06
    POSITIVE LOGITS
     examinations
    0.06
     Incident
    0.06
    融
    0.06
     Sid
    0.06
    "fmt
    0.06
    (frame
    0.06
    0.06
     Relay
    0.06
     sb
    0.06
     respondents
    0.06
    Act Density 0.001%

    No Known Activations