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

    Neuronpedia

    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     дек
    -0.07
    imens
    -0.07
    dbus
    -0.07
    ngine
    -0.06
    맹
    -0.06
    แจ
    -0.06
    ktop
    -0.06
     nerves
    -0.06
    nou
    -0.06
    POSITIVE LOGITS
    .brand
    0.07
    .DOWN
    0.06
    .H
    0.06
    (P
    0.06
     reads
    0.06
    .L
    0.06
     con
    0.06
    Sl
    0.06
     pl
    0.06
    にな
    0.06
    Act Density 0.022%

    No Known Activations