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

    Neuronpedia

    INDEX
    Explanations

    legal exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plunged
    -0.07
     heels
    -0.06
    zzarella
    -0.06
     MMI
    -0.06
    ors
    -0.06
    guards
    -0.06
    .Compose
    -0.06
    .week
    -0.06
    rieving
    -0.06
    peek
    -0.06
    POSITIVE LOGITS
    ็กซ
    0.07
    ollect
    0.07
     करक
    0.06
     exactly
    0.06
     кос
    0.06
     verdad
    0.06
    913
    0.06
     Leer
    0.06
     texte
    0.06
    разу
    0.06
    Act Density 0.022%

    No Known Activations