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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heads
    -0.08
     Medina
    -0.07
     以
    -0.07
    _attempts
    -0.06
     supremacist
    -0.06
     compel
    -0.06
     오후
    -0.06
     transistor
    -0.06
    _land
    -0.06
     갖
    -0.06
    POSITIVE LOGITS
     Newsletter
    0.07
     sure
    0.06
    reds
    0.06
     babes
    0.06
    esimal
    0.06
     occult
    0.06
     debugging
    0.06
     cute
    0.06
     poor
    0.06
     NPC
    0.06
    Act Density 0.034%

    No Known Activations