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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     werd
    -0.08
    ewith
    -0.07
    46
    -0.07
     mars
    -0.07
     cloud
    -0.07
    vue
    -0.06
     movimiento
    -0.06
     denotes
    -0.06
    <bits
    -0.06
    foreign
    -0.06
    POSITIVE LOGITS
    “That
    0.07
     stuck
    0.07
     sure
    0.07
    不足
    0.07
    Advice
    0.07
    arb
    0.07
     Tip
    0.07
    "That
    0.07
     Duty
    0.06
    /mat
    0.06
    Act Density 0.035%

    No Known Activations