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

    Neuronpedia

    INDEX
    Explanations

    requires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .with
    -0.07
    LAN
    -0.06
     TERMIN
    -0.06
    Tenant
    -0.06
    aturdays
    -0.06
    .started
    -0.06
    (internal
    -0.06
     ferv
    -0.06
    TeX
    -0.06
    xF
    -0.06
    POSITIVE LOGITS
     Nightmare
    0.07
    pch
    0.06
    Returning
    0.06
     existence
    0.06
     orth
    0.06
    ierung
    0.06
     (!
    0.06
     Grave
    0.06
     Chem
    0.06
    уванні
    0.06
    Act Density 0.040%

    No Known Activations