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

    Neuronpedia

    INDEX
    Explanations

    organization membership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     koch
    -0.86
     broderie
    -0.82
    вок
    -0.82
    вить
    -0.80
     ortaya
    -0.77
     新宿
    -0.76
    caval
    -0.76
     unreleased
    -0.76
     Stornier
    -0.75
    JsonIgnore
    -0.75
    POSITIVE LOGITS
     membership
    3.30
    membership
    2.64
     Membership
    2.56
    Membership
    2.56
     MEMBERSHIP
    2.33
     admission
    2.27
     memberships
    2.16
     Admission
    2.00
     accession
    1.92
    Admission
    1.91
    Act Density 0.023%

    No Known Activations