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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Want
    -0.07
    德拉
    -0.07
    ovation
    -0.07
    貓
    -0.07
     discard
    -0.07
     опас
    -0.07
     BER
    -0.06
    ENTITY
    -0.06
    哟
    -0.06
     Carson
    -0.06
    POSITIVE LOGITS
    .mk
    0.07
    �
    0.06
     �
    0.06
    两年前
    0.06
    .INPUT
    0.06
     reminding
    0.06
     stringValue
    0.06
    ショ
    0.06
    斶
    0.06
    ?>
↵
↵
    0.06
    Act Density 0.002%

    No Known Activations