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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ListModel
    -0.07
     Socorro
    -0.07
     tutoring
    -0.06
    edback
    -0.06
    HDR
    -0.06
    ίνεται
    -0.06
    仁
    -0.06
    Devices
    -0.06
     stark
    -0.06
     pred
    -0.06
    POSITIVE LOGITS
    (cnt
    0.07
     SEXP
    0.07
     
    0.07
    ipa
    0.06
    .mybatis
    0.06
    erable
    0.06
    undreds
    0.06
     sage
    0.06
    inh
    0.06
    Ability
    0.06
    Act Density 0.084%

    No Known Activations